{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_q2fvkqsrmngp","handle":"llm-pricing","url":"https://wellknown.network/agents/llm-pricing","links":{"self":"https://wellknown.network/agents/llm-pricing/record.json","html":"https://wellknown.network/agents/llm-pricing","markdown":"https://wellknown.network/agents/llm-pricing/record.md","api":"https://wellknown.network/api/v1/agents/llm-pricing","status":"https://wellknown.network/api/v1/agents/llm-pricing/status","claim":"https://wellknown.network/agents/llm-pricing/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/llm-pricing/claim.json","badge":"https://wellknown.network/agents/llm-pricing/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/llm-pricing/history","tools":"https://wellknown.network/api/v1/agents/llm-pricing/tools"},"ard":{"identifier":"urn:air:llm-pricing-api.fly.dev:server:llm-pricing","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"LLM Pricing","summary":"Real-time, drift-verified LLM pricing across 26 providers with cost+quality model routing.","description":"Real-time, drift-verified LLM pricing across 26 providers with cost+quality model routing.","publisher":{"name":"skakumanu","url":null},"homepage":null,"repository":"https://github.com/skakumanu/llm-pricing-mcp-server","version":"1.73.2","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://llm-pricing-api.fly.dev/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-10-19T04:54:31.614243Z","publishedAt":"2026-10-19T04:54:31.614243Z","registryName":"io.github.skakumanu/llm-pricing-mcp-server"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":1,"provenance":"derived"},{"slug":"commerce.pricing","name":"Pricing & Quotes","confidence":1,"provenance":"derived"},{"slug":"communication.notifications","name":"Notifications","confidence":1,"provenance":"derived"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.54,"provenance":"derived"},{"slug":"content.writing","name":"Writing & Editing","confidence":0.51,"provenance":"derived"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":0.51,"provenance":"derived"}],"categories":["commerce","communication","content","dev","documents","infra"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 2h ago.","lastOkAt":"2026-10-23T19:28:01.308Z","lastProbedAt":"2026-10-23T19:28:01.308Z","statusComputedAt":"2026-10-23T19:31:11.375Z","reliability30d":{"probes":12,"successRate":1,"p50Ms":127,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":12,"ok":12,"authBoundaryOk":0,"serviceOk":12,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-10-23T19:28:01.308Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":116,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.5","protocolVersion":"2024-11-05"}},{"at":"2026-10-23T12:27:15.857Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":102,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.5","protocolVersion":"2024-11-05"}},{"at":"2026-10-23T05:30:03.568Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":98,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.5","protocolVersion":"2024-11-05"}},{"at":"2026-10-22T22:27:54.958Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":107,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.4","protocolVersion":"2024-11-05"}},{"at":"2026-10-22T16:28:56.090Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":110,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.4","protocolVersion":"2024-11-05"}},{"at":"2026-10-22T09:30:33.483Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":119,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.4","protocolVersion":"2024-11-05"}},{"at":"2026-10-22T03:32:24.270Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":203,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.3","protocolVersion":"2024-11-05"}},{"at":"2026-10-21T21:35:50.482Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":184,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.3","protocolVersion":"2024-11-05"}},{"at":"2026-10-21T12:25:38.923Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":187,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.3","protocolVersion":"2024-11-05"}},{"at":"2026-10-21T03:25:30.453Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":325,"error":null,"detail":{"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"toolCount":29,"toolsHash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","serverName":"LLM Pricing MCP Server","capabilities":["tools"],"serverVersion":"1.73.3","protocolVersion":"2024-11-05"}}],"tools":[{"name":"get_all_pricing","description":"Get current pricing for all LLM models from all providers"},{"name":"estimate_cost","description":"Estimate the cost of using a specific LLM model"},{"name":"compare_costs","description":"Compare costs for multiple LLM models"},{"name":"get_performance_metrics","description":"Get performance metrics (throughput, latency, context window) for models"},{"name":"get_use_cases","description":"Get recommended use cases and strengths for LLM models"},{"name":"get_telemetry","description":"Get MCP server telemetry and usage statistics including tool usage, response times, and error rates"},{"name":"get_pricing_history","description":"Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given n"},{"name":"get_pricing_trends","description":"Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'd"},{"name":"register_price_alert","description":"Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provi"},{"name":"list_price_alerts","description":"List all registered price-change webhook alerts with their IDs and settings."},{"name":"delete_price_alert","description":"Delete a registered price-change alert by its ID."},{"name":"get_pricing_export_url","description":"Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) "},{"name":"list_conversations","description":"List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user"},{"name":"delete_conversation","description":"Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the "},{"name":"get_ide_pricing","description":"Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly su"},{"name":"predict_cost","description":"Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or acc"},{"name":"optimize_workload","description":"Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of work"},{"name":"recommend_model","description":"Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies th"},{"name":"check_price_drift","description":"Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with "},{"name":"get_data_quality","description":"Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to "},{"name":"get_cache_stats","description":"Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /r"},{"name":"record_usage","description":"Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend"},{"name":"get_usage_summary","description":"Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usag"},{"name":"analyze_session_usage","description":"Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a p"},{"name":"import_session_usage","description":"Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a "},{"name":"register_budget_alert","description":"Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope"},{"name":"list_budget_alerts","description":"List all registered budget-spend webhook alerts with their IDs and settings."},{"name":"delete_budget_alert","description":"Delete a registered budget-spend alert by its ID."},{"name":"ask_agent","description":"Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything"}],"package":null,"toolSurface":{"id":"ts_mccuk4wgjetw","endpointId":"ep_b7k3cpnvz698","hash":"564a2ecb177acccffee5abe7e0f6e8ce028efdcfe29c0cfc138d8f38ddf0c1bb","toolCount":29,"serverName":"LLM Pricing MCP Server","serverVersion":"1.73.2","protocolVersion":"2024-11-05","firstSeenAt":"2026-10-20T13:29:51.243Z","lastSeenAt":"2026-10-23T19:28:01.315Z","observations":12,"toolNames":["get_all_pricing","estimate_cost","compare_costs","get_performance_metrics","get_use_cases","get_telemetry","get_pricing_history","get_pricing_trends","register_price_alert","list_price_alerts","delete_price_alert","get_pricing_export_url","list_conversations","delete_conversation","get_ide_pricing","predict_cost","optimize_workload","recommend_model","check_price_drift","get_data_quality","get_cache_stats","record_usage","get_usage_summary","analyze_session_usage","import_session_usage","register_budget_alert","list_budget_alerts","delete_budget_alert","ask_agent"],"distinctSurfaces":1},"endpointFacts":[{"id":"ep_b7k3cpnvz698","url":"https://llm-pricing-api.fly.dev/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-10-21T12:25:38.956Z","auth":{"observedAt":"2026-10-21T12:25:39.062Z","authRequired":false,"scheme":null,"resourceMetadata":null,"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":false,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-10-21T12:25:39.083Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"*.fly.dev","issuer":{"commonName":"YE1","organization":"Let's Encrypt"},"validFrom":"2026-08-21T11:49:33.000Z","validTo":"2026-11-19T11:49:32.000Z","daysToExpiry":26,"sanCount":1,"fingerprint256":"25:9A:3B:9C:DA:F4:BA:BB:BE:5E:B7:81:BE:23:8A:52:12:15:DF:90:AF:E8:F5:15:17:99:30:F2:A6:A8:59:B4"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"io.github.skakumanu/llm-pricing-mcp-server","url":"https://registry.modelcontextprotocol.io/v0/servers/io.github.skakumanu%2Fllm-pricing-mcp-server","firstSeenAt":"2026-10-20T13:23:12.128Z","fetchedAt":"2026-10-20T13:23:12.128Z","normalizedAt":"2026-10-20T13:23:12.128Z"}]},"firstSeenAt":"2026-10-20T13:23:12.128Z","updatedAt":"2026-10-23T19:33:02.910Z"}