Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Added "ai_answer", "ai_fact_check", "ai_moderation" and 1 more; changed the definition of "ai_chat" (21 tools before, 25 now)
⟨14 unchanged words⟩ "minimum":-9007199254740991,"type":"integer"},"messages":{"description":"Optional OpenAI messages array as JSON (system, user, assistant with tool_calls, tool); replaces prompt and system. Together with tools, at most 20,000 characters","type":"string"},"prompt":{"description":"User prompt, up to 8,000 characters","type":"string"},"response_format":{"description":"Optional OpenAI response_format as JSON: {\"type\":\"json_object\"} or a json_schema","type":"string"},"system":{"description":"Optional system prompt, ⟨9 unchanged words⟩ "0-1.5 (default 0.6)","type":"number"},"tool_choice":{"description":"Optional: auto, none, required, or a JSON object naming one function","type":"string"},"tools":{"description":"Optional OpenAI tools array as JSON (function calling, up to 32 functions); the answer then carries tool_calls","type":"string"}},"required":["prompt"],"type":"object"}
Web answer, AI with citations: answer a question from live search results — Answer a question from the live web in one call: a Brave web search, the top result pages read, and an answer written by Llama 4 Scout from those sources only, with inline [n] citations and the source list (title, URL). Says so when the sources do not answer it. Results are for the caller's immediate use only: no storing, resale or model training (Brave API terms). Use when an agent needs a current, sourced answer rather than raw search results. Example: q=What is the x402 payment protocol?. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and…
Fact check, verify a claim: against live web sources — Check a claim against the live web in one call: a Brave search, the top pages read, and a verdict from Llama 4 Scout using those sources only (supported, contradicted, mixed or unverified) with a short explanation, [n] citations and the sources. A model's reading of a few search results, not an editorial fact-check. Results are for immediate use only (Brave API terms). Use to screen a statement before an agent repeats or acts on it. Example: claim=The x402 protocol uses the HTTP 402 Payment Required status code.. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Read…
Content moderation, safety check: Llama Guard 3 — Classify a text as safe or unsafe with Meta's Llama Guard 3 and name the hazard categories it falls into (violent and non-violent crimes, sexual content, child exploitation, hate, self-harm, weapons, privacy, defamation, elections and others; 14 in all). Up to 8,000 characters. Also available in the OpenAI moderation shape at /v1/moderations. Use to screen user messages, model outputs or content before an agent posts or acts on it. Example: text=How do I bake sourdough bread at home?. Price $0.002/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes…
Rerank documents by relevance: reranker for RAG — Order up to 50 documents by how well each answers a query, with a relevance score from 0 to 1 (BAAI bge-reranker-base, a cross-encoder). Send documents as a JSON array or one per line; each is read up to 2,000 characters, 40,000 in all. Returns the original index, score and text, best first; top_n keeps only the best. Also available in the Cohere-style shape at /v1/rerank. Use to pick what a model reads after search or vector retrieval. Price $0.002/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, …
Added "ai_model_deepseek_r1", "ai_model_gpt_oss_120b", "ai_model_gpt_oss_20b" and 3 more; changed the definition of "ai_chat", "ai_classify", "ai_embed" and 10 more (15 tools before, 21 now)
LLM chat completions, inference: Llama3.148BScout
Send a prompt, get an answer from Meta's Llama3.148BScoutInstruct(17B active, 16 experts),
Recently observed → Live
Changed the definition of "ai_chat", "ai_chat_large", "image" and 1 more
LLM chat completions, inference: Llama 3.1 8B
⟨6 unchanged words⟩ "readOnlyHint":true,"title":"LLM chat completions, inference: Llama 3.1 8B"}
ChatLLMcompletion
Live → Recently observed
Certificate recorded, valid to 2027-01-07
Authorization not required
Changed the definition of "ai_chat"
⟨46 unchanged words⟩ Example: prompt=Explain x402 in one sentence.. Price$0.01/call$0.002/call via x402 USDC or a card key ( ⟨21 unchanged words⟩
Changed the definition of "ai_classify", "ai_extract_json" and "ai_keywords"
ClassifyTexttextclassification intoyourlabels
⟨4 unchanged words⟩ openWorldHint":true,"readOnlyHint":true,"title":"ClassifyTexttextclassification intoyourlabels"}
Unknown → Live
First tool surface recorded: 15 tools (server version 1.50.2)
https://agent-data-tools.revmesh2074.workers.dev/mcp/ai (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 12 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨6 unchanged words⟩ "readOnlyHint":true,"title":"LLM chat completions, inference: Llama3.148BScout"}
⟨32 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨37 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨39 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨25 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨39 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨43 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨41 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨52 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨39 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨49 unchanged words⟩ x402 USDC or a card key (/credits);, first 25 free; failed calls free. Reads or computes only and ⟨11 unchanged words⟩
⟨42 unchanged words⟩ on a cliff at sunset, watercolor. Price$0.02/call$0.01/call via x402 USDC or a card key ( ⟨21 unchanged words⟩
⟨46 unchanged words⟩ voice messages. Example: url=https://commons.wikimedia.org/wiki/Special:FilePath/En-us-hello.ogg. Price$0.02/call$0.01/call via x402 USDC or a card key ( ⟨21 unchanged words⟩
DeepSeek R1 reasoning model API: pay per call, no API key — Chat with DeepSeek's R1 reasoning model distilled into Qwen 32B (MIT) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 2,048 output tokens; its reasoning is removed from the answer. Also reachable as model "deepseek-r1" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name. Example: prompt=Explain x402 in one sentence.. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
GPT-OSS 120B chat API: pay per call, no API key — Chat with OpenAI's open-weight gpt-oss-120b reasoning model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens. Also reachable as model "gpt-oss-120b" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name. Example: prompt=Explain x402 in one sentence.. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
GPT-OSS 20B chat API: pay per call, no API key — Chat with OpenAI's open-weight gpt-oss-20b reasoning model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens. Also reachable as model "gpt-oss-20b" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name. Example: prompt=Explain x402 in one sentence.. Price $0.002/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
Mistral Small 3.1 chat API: pay per call, no API key — Chat with Mistral AI's Mistral Small 3.1 24B model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens. Also reachable as model "mistral-small" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name. Example: prompt=Explain x402 in one sentence.. Price $0.005/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
Qwen3 30B chat API: pay per call, no API key — Chat with Alibaba's Qwen3 30B-A3B mixture-of-experts model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens; its reasoning is removed from the answer. Also reachable as model "qwen3-30b" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name. Example: prompt=Explain x402 in one sentence.. Price $0.002/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
Qwen2.5 Coder 32B, code LLM API: pay per call, no API key — Chat with Alibaba's Qwen2.5 Coder 32B code model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens. Also reachable as model "qwen-coder" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name. Example: prompt=Explain x402 in one sentence.. Price $0.005/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.
⟨4 unchanged words⟩ openWorldHint":true,"readOnlyHint":true,"title":"ChatLLMcompletioninference,(large model: Llama 3.3 70B or gpt-oss-120b)"}
Image generation, generate image from a text prompt
⟨5 unchanged words⟩ true,"readOnlyHint":true,"title":"Image generation, generate image from a text prompt"}
TranscribeSpeech to text, transcribe audio:speech toWhispertexttranscriptionforof an audio file
⟨4 unchanged words⟩ openWorldHint":true,"readOnlyHint":true,"title":"TranscribeSpeech to text, transcribe audio:speech toWhispertexttranscriptionforof an audio file"}
Extract JSON fields from textas JSON
⟨5 unchanged words⟩ :true,"readOnlyHint":true,"title":"Extract JSON fields from textas JSON"}
ExtractKeywordkeywordsextraction
⟨4 unchanged words⟩ openWorldHint":true,"readOnlyHint":true,"title":"ExtractKeywordkeywordsextraction"}