mcpField
S
Synap

Synap

Remote
synap.linkrra.comAI & Agents0Updated 1w ago

About Synap

Synap is an MCP server that gives AI agents access to open models through an OpenAI-compatible API. It provides model discovery, pricing and cost estimates, plus chat completion through hosted HTTP or a stdio bridge.

Key features

  1. 01List available models
  2. 02View model prices and limits
  3. 03Estimate job costs
  4. 04Run chat completions
  5. 05Hosted HTTP and stdio access

Use cases

  1. 01Compare models before choosing one
  2. 02Estimate a task’s cost before running it
  3. 03Run model chat completions from an agent

MCP support

Exposes tools to list and inspect models, estimate costs, and run chat completions. It is available as a hosted Streamable HTTP server and through a stdio bridge that forwards requests to the hosted endpoint.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://pool.linkrra.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://pool.linkrra.com/mcpAuth required

Tools

4
ParameterTypeRequiredDescription
modelstringYesModel 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.
messagesarrayYesThe conversation so far, oldest first. The last message is normally the user turn to answer.
max_tokensintegerNoUpper limit on tokens generated in the reply. Omit to use the model default; lower it to cap cost.
temperaturenumberNoSampling randomness, 0 to 2. Lower is more deterministic. Omit to use the model default.

Details

From the project README

Synap MCP server

Synap by Linkrra as a Model Context Protocol server: open models behind one OpenAI-compatible API. Your agent can list the models we serve, read their prices and limits, estimate the cost of a job before running it, and run a chat completion.

There is one server, hosted at https://pool.linkrra.com/mcp (Streamable HTTP). It is the server behind com.linkrra/synap in the official MCP registry.

This repository has two parts:

  • routes.js is the deployed router itself, byte for byte.
  • bin/synap-mcp.js is the stdio transport (npx synap-mcp) for MCP hosts that launch a local command. It sends every message to the hosted server unchanged, so it always exposes the same tools as the hosted server.

Tools

ToolCostKey needed
synap_list_modelsfreeno
synap_get_modelfreeno
synap_estimate_costfreeno
synap_chat_completionbilled per prompt and completion tokenyes

Model ids are the ones synap_list_models returns. Pass synap-v1 and Synap picks the cheapest model that can do the job.

Connect

Hosted (Streamable HTTP), no install needed
{
  "mcpServers": {
    "synap": {
      "type": "http",
      "url": "https://pool.linkrra.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_SYNAP_API_KEY" }
    }
  }
}
Local stdio (Claude Desktop, Cursor, Cline, Windsurf, Zed)
{
  "mcpServers": {
    "synap": {
      "command": "npx",
      "args": ["-y", "synap-mcp"],
      "env": { "SYNAP_API_KEY": "YOUR_SYNAP_API_KEY" }
    }
  }
}

Without a key, the three free tools still work. synap_chat_completion returns an error and nothing is charged.

VariableMeaning
SYNAP_API_KEYYour Synap key, sent as Authorization: Bearer. Get one at https://synap.linkrra.com.
SYNAP_MCP_URLOptional. Overrides the endpoint (default https://pool.linkrra.com/mcp).

Use it from goose

A ready-made goose custom-provider file lives in goose/. Download goose/linkrra.json into ~/.config/goose/custom_providers/, set LINKRRA_API_KEY, and pick Linkrra (Synap) as the provider. Full setup steps and the model table: goose/README.md.

Paying

  • API key (MCP and REST). Top up a Synap account by card or crypto. Each call is billed per token against that balance. MCP always uses this method.
  • x402, no account. An agent with a USDC wallet on Base can pay per call over plain HTTP at POST https://pool.linkrra.com/api/billing/x402/chat/completions. An unpaid request returns 402 with the payment terms. This route is part of the REST API, not an MCP tool. Its settlement is independently verified on PayAPI Market.

Protocol

The hosted server speaks both MCP eras:

  • 2026-07-28 (current): stateless. It implements server/discover and reads the per-request _meta protocol version. It checks that MCP-Protocol-Version, Mcp-Method and Mcp-Name match the request body. Results carry resultType, and list results also carry ttlMs and cacheScope.
  • 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05: the initialize handshake.

The bridge works with both. For a legacy client, it remembers the version agreed during initialize. For a 2026-07-28 client, it copies the _meta version into the HTTP headers that the Streamable HTTP transport requires.

The API behind it

https://pool.linkrra.com/v1 is an OpenAI-compatible API. On every self-hosted model it supports tool calling (tools, tool_choice) and structured outputs (response_format json_object / json_schema). Requests can be streamed or not. Prompts and completions are not stored.

Auth

The server passes your key through and nothing else. The key travels in the standard Authorization: Bearer header, the same way it would on a direct call to /v1/chat/completions. routes.js forwards that header untouched. The server never reads, stores or creates a key.

Run the server standalone

npm install && npm start     # serves :8080/mcp

Develop

npm test     # offline: a local mock checks the bridge's headers for both protocol eras

The stdio bridge needs Node 18 or later and has no dependencies.

License

Apache-2.0

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.