Skip to content

MCP Proxy

An MCP proxy server that aggregates and serves multiple MCP resource servers through a single HTTP server.

Install

$go install github.com/tbxark/mcp-proxy@latest

Install command taken from the project's README or registry entry. Always review code before running it.

MCP Proxy Server

An MCP proxy that aggregates multiple MCP servers behind a single HTTP entrypoint.

Features

  • Proxy multiple MCP clients: aggregate tools, prompts, and resources from many servers.
  • SSE and streamable HTTP: serve via Server‑Sent Events or streamable HTTP.
  • Flexible config: supports stdio, sse, and streamable-http client types.
  • OAuth client support: authorize once against downstream servers that require interactive OAuth (e.g. Notion), then let the proxy hold and refresh the token for every caller.

Documentation

Quick Start

Build from source

git clone https://github.com/tbxark/mcp-proxy.git
cd mcp-proxy
make build
./build/mcp-proxy --config path/to/config.json

Install via Go

go install github.com/tbxark/mcp-proxy@latest

Docker

The image includes support for launching MCP servers via npx and uvx.

docker run -d -p 9090:9090 -v /path/to/config.json:/config/config.json ghcr.io/tbxark/mcp-proxy:latest
# or provide a remote config
docker run -d -p 9090:9090 ghcr.io/tbxark/mcp-proxy:latest --config https://example.com/config.json

More deployment options (including docker‑compose) are in docs/deployment.md.

Configuration

See full configuration reference and examples in docs/configuration.md. An online Claude config converter is available at: https://tbxark.github.io/mcp-proxy

Usage

Command‑line flags, endpoints, and auth examples are documented in docs/usage.md.

Thanks

License

This project is licensed under the MIT License. See the LICENSE file for details.

Similar plugs

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…

Explore related