广告合作
MCP.so
登录

MCP Bridge

@SecretiveShell

代码仓库

基本信息

分类

开发工具

许可证

MIT

传输方式

stdio

作者

SecretiveShell

关于 MCP Bridge

A middleware to provide an openAI compatible endpoint that can call MCP tools

#ai#mcp#openai#claude#openai-api#model-context-protocol#mcp-servers#mcp-server

MCP Bridge 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "MCP-Bridge": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

MCP Bridge 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP-Bridge?

MCP-Bridge acts as a bridge between the OpenAI API and MCP (Model Context Protocol) tools, enabling developers to leverage MCP tools through the OpenAI API interface. It is designed for developers who want to use any OpenAI-compatible client with MCP tools without requiring explicit MCP support in the client.

How to use MCP-Bridge?

Recommended installation is via Docker: clone the repository, edit the compose.yml file to reference a config.json (via volume mount, HTTP URL, or environment variable), then run docker-compose up --build -d. For manual installation, clone the repo, run uv sync, create a config.json, and execute uv run mcp_bridge/main.py. Once running, interact with the OpenAI API at http://yourserver:8000/docs. Configuration requires specifying an inference_server and mcp_servers in the config file; API key authentication is optional.

Key features of MCP-Bridge

  • Non‑streaming chat completions with MCP tools
  • Streaming chat completions with MCP tools
  • Non‑streaming completions without MCP
  • MCP sampling support
  • SSE bridge for external MCP clients
  • REST API endpoints for all MCP primitives
  • API key authentication

Use cases of MCP-Bridge

  • Use any OpenAI‑compatible client (e.g., Open Web UI) with MCP tools
  • Outsource MCP server complexity to a central bridge
  • Test MCP server configurations via SSE with tools like mcp-cli
  • Use MCP tools inside STDIO‑only clients (e.g., Claude Desktop) via a gateway

常见问题

1

Is MCP-Bridge still actively maintained?

MCP-Bridge is looking for new maintainers. Open WebUI natively supports MCP starting in v0.6.31, so MCP-Bridge is considered soft deprecated.

2

What are the runtime requirements?

It requires an inference engine with tool call support (tested with vLLM; ollama is likely compatible). Docker is the recommended installation method.

3

Where does the configuration live?

Configuration is stored in a `config.json` file, which can be provided as a volume mount, downloaded from an HTTP URL, or set as a JSON environment variable.

4

What transports and authentication does it support?

It supports an SSE bridge (`/mcp-server/sse`) for external MCP clients. Authentication is enabled via API keys passed as a Bearer token in the `Authorization` header.

5

What are the known limitations?

Streaming completions without MCP are not yet implemented. MCP resource support is planned but not currently available.

评论

开发工具 分类下的更多 MCP 服务器

Modelglass

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

1

Skilder.ai

skilder.ai

Run skills and MCP tools like production software: versioned, composed into roles, distributed to every agent from one governed library.

Capgo MCP

Cap-go

Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Meticulous

Meticulous

Ybug

Ybug

Connect Claude, ChatGPT, Cursor or any MCP client to Ybug. Read bug reports with screenshots, console logs and network requests, then triage them in chat.

广告合作