Synap

Send a conversation to a model on Synap, Linkrra's OpenAI-compatible inference API, and get the model's reply. Use this when you need text generated, code written or a question answered by one of the open models Synap serves. This 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 MCP 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.

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id exactly as returned by synap_list_models, e.g. \"qwen3-coder-30b\". Use \"synap-v1\" to let Synap pick the cheapest model that can handle the request."
    },
    "messages": {
      "type": "array",
      "description": "The conversation so far, oldest first. The last message is normally the user turn to answer.",
      "minItems": 1,
      "items": {
        "type": "object",
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "system",
              "user",
              "assistant"
            ],
            "description": "Who wrote the message: system (instructions), user, or assistant (an earlier model reply)."
          },
          "content": {
            "type": "string",
            "description": "The message text."
          }
        },
        "required": [
          "role",
          "content"
        ]
      }
    },
    "temperature": {
      "type": "number",
      "minimum": 0,
      "maximum": 2,
      "description": "Sampling randomness, 0 to 2. Lower is more deterministic. Omit to use the model default."
    },
    "max_tokens": {
      "type": "integer",
      "minimum": 1,
      "description": "Upper limit on tokens generated in the reply. Omit to use the model default; lower it to cap cost."
    }
  },
  "required": [
    "model",
    "messages"
  ]
}

List the models Synap serves right now, 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 ("synap-v1"), which bill at the price of the model they route to. For every field of one model use synap_get_model.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Optional case-insensitive filter matched against model id, name and capability, e.g. \"coder\", \"qwen\" or \"vision\". Omit to list everything."
    }
  }
}

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.

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id exactly as returned by synap_list_models."
    }
  },
  "required": [
    "model"
  ]
}

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.

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id exactly as returned by synap_list_models."
    },
    "prompt_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Tokens you will send (system + conversation). Roughly 4 characters of English per token."
    },
    "completion_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Tokens you expect back. Use your max_tokens for a worst case. Defaults to 0."
    }
  },
  "required": [
    "model",
    "prompt_tokens"
  ]
}