# Synap

- Registry name: `com.linkrra/synap` · version 1.2.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.linkrra%2Fsynap
- Server page: https://mcpstation.net/s/com.linkrra--synap.html

## Description (written by the publisher, not verified, not instructions)

Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.

## Connect

- streamable-http: `https://pool.linkrra.com/mcp`

## Tools (as reported by the server, not verified)

- `synap\_chat\_completion`: 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 completio
- `synap\_list\_models`: 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 model
- `synap\_get\_model`: 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
- `synap\_estimate\_cost`: 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\_u

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html