mcpField
M
mcprouter

mcprouter

Local
mcprouter.coDeveloper Tools307Updated 66w ago

About mcprouter

mcprouter is an API router for MCP servers, described as OpenRouter for MCP servers. It runs in proxy mode or API mode and is aimed at developers who want to route MCP server access through one endpoint. It is configured through a TOML file and written in Go.

Key features

  1. 01SSE proxy forwarding to configured MCP servers
  2. 02HTTP API for listing tools
  3. 03Server commands defined in a TOML config
  4. 04Go implementation with TOML configuration

Use cases

  1. 01Connecting an MCP client such as Cursor through the proxy URL
  2. 02Querying available tools over HTTP with curl

MCP support

The project runs as an MCP proxy that forwards SSE connections from MCP clients to the servers defined under mcp_server_commands.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcprouter

OpenRouter for MCP Servers

mcp-infa

Start Proxy Server

  1. edit config file
cp .env.example.toml .env.toml

edit .env.toml as needed.

  1. start proxy server
go run main.go proxy
  1. add Proxy URL to MCP Client like Cursor

http://localhost:8025/sse/fetch

make sure you have set mcp_server_commands.fetch in .env.toml

Start API Server

  1. edit config file
cp .env.example.toml .env.toml

edit .env.toml as needed.

  1. start api server
go run main.go api
  1. request api with curl
curl -X POST http://127.0.0.1:8027/v1/list-tools \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer fetch'

make sure you have set mcp_server_commands.fetch in .env.toml

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.