Synap402 logo

Synap402

Connects MCP clients to Synap for model discovery, cost estimates, and OpenAI-compatible chat completions.

Install Synap402

Pick your client, then add it in one click or paste the config.

Streamable HTTP (Remote)
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "synap402": {
      "command": "npx",
      "args": [
        "-y",
        "synap-mcp"
      ],
      "env": {
        "SYNAP_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Hosted endpointLive · 1d agoLive Remote EndpointOur automated health check connected to this remote MCP endpoint successfully.Last checked 1d ago · Nov 16, 2026, 22:15 UTC

Clients with native remote MCP support can connect directly to this URL.

Remote endpoint
https://synap402.com/mcp
We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y synap-mcp

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked .

Overview

Synap402 MCP server connects MCP clients to Linkrra Synap, an OpenAI-compatible inference API for open models including Qwen, Gemma, GLM, and DeepSeek. It provides free model discovery and cost-estimation tools alongside a paid, non-streamed chat completion tool. Use the hosted Streamable HTTP endpoint or run the npm package locally with npx. It fits conversational AI workflows that need model selection, token-price checks, and generated text through Synap.

Use cases

  • List available Synap models before selecting one for a task
  • Estimate prompt and completion costs before running inference
  • Inspect model limits and data-retention policies
  • Send full conversations to open models for generated text or code

Key features

  • Live model catalogue with per-token pricing
  • Detailed model records and limits
  • Pre-request USD cost estimation
  • OpenAI-compatible chat completion responses
  • Hosted Streamable HTTP endpoint
  • Local npx-based launch

Tools4

What Synap402 lets your agent do. Expand a tool for its parameters.

Verified live~1.1k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

What it can do

From the 4 tools this server returned when we ran it.

Handles credentials · 4Read-only tools · 4

Observed 2026-11-12 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 6d ago via OSV.dev · synap-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads642Package downloads in the last 30 days.
Last commit6d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed4Callable tools this server registers over MCP.
Directory activity1 installsConfig copies, upvotes, and views on AllMCPs.

How Synap402 works

What Synap402 does

Synap402 exposes Linkrra Synap’s open-model inference API through MCP. The available models include families such as Qwen, gpt-oss, Gemma, GLM, and DeepSeek. Agents can inspect the live catalogue, compare token prices, check model limits, estimate a request’s cost, and submit conversations for completion.

The server separates free catalogue operations from inference. Listing models, retrieving a model record, and estimating a completion cost do not require an API key and do not run a model. Chat completion is the billable operation: it uses the Synap API key supplied as a Bearer token and charges for prompt and completion tokens.

How it works

A client can call synap_list_models to obtain currently served model IDs, capabilities, context sizes, output limits, tiers, pricing, and data-policy information. Because the catalogue is live, the available set can change between calls. synap_get_model returns the full record for one model, including supported parameters, quantisation, readiness, pricing, token limits, and retention policy.

For budget checks, synap_estimate_cost calculates prompt, completion, and total USD amounts from token counts and the live price list. The estimate is not the final charge; the eventual request uses the token counts reported by the model. Auto-routing IDs such as synap-v1 have no fixed price and cannot be estimated with this tool.

synap_chat_completion accepts the conversation and selected model, then returns a standard OpenAI chat.completion response. The reply is available in choices[0].message.content, with token usage in usage. Requests are not streamed, and the server keeps no conversation memory, so each call must include the complete message history.

Setup and configuration

Use the hosted Streamable HTTP endpoint at https://synap402.com/mcp when the MCP client can connect to a remote server. For a local launch, run the npm package with:

Terminal
npx -y synap-mcp

A local client configuration can start the package and pass the credential through SYNAP_API_KEY:

config.json
{
  "mcpServers": {
    "synap": {
      "command": "npx",
      "args": ["-y", "synap-mcp"],
      "env": { "SYNAP_API_KEY": "sk-..." }
    }
  }
}

The key is used for chat completion authorization. Without a key, catalogue and pricing tools remain usable, while a chat request returns an error and spends nothing. A key without sufficient balance returns insufficient_credits.

Tools and capabilities

  • synap_list_models — Lists live model IDs, capabilities, context and output limits, prices, tiers, and data policies.
  • synap_get_model — Retrieves the complete catalogue entry for one model.
  • synap_estimate_cost — Estimates prompt, completion, and total cost from token counts.
  • synap_chat_completion — Sends a full conversation to a Synap model and returns an OpenAI-compatible completion.

Limitations and notes

Chat completion is the only paid tool and is not streamed. The server does not retain conversation state, so callers must provide prior messages on every request. Prices and model availability can change because the model list is live. Auto-routing models without fixed pricing cannot be evaluated by the cost-estimation tool. A model must be selected from the models Synap currently serves; an unknown ID produces an error from the model lookup tool.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Synap402

Synap402 is an MCP server that connects MCP clients to Linkrra Synap, an OpenAI-compatible inference API for open models. Its tools list live models and prices, inspect model records, estimate request costs, and run non-streamed chat completions. Model discovery and estimates are free; completions require a Synap402 API key and consume credits.

Run `npx -y synap-mcp` for a local launch, then configure the MCP client to start that command and set `SYNAP_API_KEY` in its environment. You can also connect to the hosted Streamable HTTP endpoint at `https://synap402.com/mcp`.

Yes, Synap402 works with Cursor. The package is listed as an MCP integration for Cursor, and the local configuration uses the `npx -y synap-mcp` command with the optional API key environment setting.

Yes, call `synap_estimate_cost` with token counts and a model that has fixed pricing. It returns prompt, completion, and total USD estimates without running a model or requiring an API key. Auto-routing IDs such as `synap-v1` cannot be estimated because their price depends on the routed model.

No, only `synap_chat_completion` requires a Synap402 API key. Model listing, detailed model lookup, and cost estimation are free and can be called without a key; an unauthenticated chat request returns an error without spending credits.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewSynap402 AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/synap402?style=directory)](https://allmcps.com/mcp/synap402)
HTML Embed
<a href="https://allmcps.com/mcp/synap402"><img src="https://allmcps.com/api/badge/synap402?style=directory" alt="Synap402 on AllMCPs" /></a>