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 "synap_estimate_cost" and "synap_get_model"; changed the definition of "synap_chat_completion" and "synap_list_models" (2 tools before, 4 now)
before
—after
Run a chat completion on SynapCallSend a conversation to a model on Synap, Linkrra's OpenAI-compatible inference API,(pool.linkrra.com/v1)and get the model's reply. Use this when you need text generated,forcode written or achatquestioncompletion.answeredRequiresby one of thecalleropentomodelssupplySynaptheirserves.ownThis is the only tool here that costs money: it bills prompt and completion tokens to the Synap API key supplied as the Authorization: Bearer header on the MCPrequest.connection. With no key it returns an error and nothing is spent; a key with no balance returns insufficient_credits. Call synap_estimate_cost first if the price matters. Returns the standard OpenAI chat.completion JSON (choices[0].message.content holds the reply, usage holds token counts). The call is not streamed and keeps no memory between calls — send the full message history each time.
{"properties":{"max_tokens":{"description":"Upper limit on tokens generated in the reply. Omit to use the model default; lower it to cap cost.","minimum":1,"type":"integer"},"messages":{"description":"The conversation so far, oldest first. The last message is normally the user turn to answer.","items":{"properties":{"content":{"description":"The message text.","type":"string"},"role":{"description":"Who wrote the message: system (instructions), user, or assistant (an earlier model reply).","enum":["system","user","assistant"] ⟨4 unchanged words⟩ ,"content"],"type":"object"},"minItems":1,"type":"array"},"model":{"description":"Model id—exactlyseeas returned by synap_list_models,fore.g. \"qwen/qwen3-coder-30b-a3b-instruct\". Use \"synap-v1\" to let Synap pick thecatalogue.cheapest model that can handle the request.","type":"string"},"temperature":{"description":"Sampling randomness, 0 to 2. Lower is more deterministic. Omit to use the model default.","maximum":2,"minimum":0,"type":"number"}},"required":[" ⟨4 unchanged words⟩
before
—after
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":false}before
—after
List Synap models and pricesList the modelscurrentlySynapavailableservesonrightSynapnow, each with its price per million tokens, context window and what it is good at. Use this to choose a model id before calling synap_chat_completion, or to compare prices. Free, read-only, no API key needed, and safe to call repeatedly; the list is live, so models can appear or go between calls. Returns {"object":"list","count":N,"data":[{id,name,capability,tier,context_tokens,max_output_tokens,pricing,data_policy}]}; pricing is USD per million prompt and completion tokens and is absent for the auto-routing ids (pool.linkrra.com/v1/models"synap-v1")., which bill at the price of the model they route to. For every field of one model use synap_get_model.
Estimate the cost of a Synap call — Work out what a chat completion would cost on Synap from token counts, using the live price list. Use this before synap_chat_completion when budget matters, or to compare models for a job. Free, read-only, needs no API key and runs no model. Returns {model, prompt_tokens, completion_tokens, prompt_usd, completion_usd, total_usd, pricing}. It is an estimate: the real charge uses the token counts the model reports afterwards. Auto-routing ids such as "synap-v1" have no fixed price and return an error saying so.
Get one Synap model in full — Return the complete catalogue record for one Synap model: pricing, context and output limits, supported parameters, quantisation, data-retention policy and readiness. Use this after synap_list_models when you need details the summary leaves out. Free, read-only and needs no API key. Returns the raw model object, or an error naming the id if Synap does not serve it.
Recently observed → Live
Live → Recently observed
Certificate recorded, valid to 2026-11-08
Authorization not required
Unknown → Live
First tool surface recorded: 2 tools (server version 1.0.0)
https://pool.linkrra.com/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 8 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
{"properties":{"query":{"description":"Optional case-insensitive filter matched against model id, name and capability, e.g. \"coder\", \"qwen\" or \"vision\". Omit to list everything.","type":"string"}},"type":"object"}
before
—after
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}