MCP-Bridge MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

Exposes MCP tools as OpenAI-style functions to any OpenAI-compatible client
REST + SSE endpoints; mirrors /v1/chat/completions
Multiple upstream MCP servers configured in one JSON
Optional bearer auth for the bridge itself
Runs as Docker container or uv sync Python app

Живое демо

Как выглядит на практике

bridge.replay ▶ готово

0/0

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "bridge": {
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ],
      "_inferred": true
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "bridge": {
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ],
      "_inferred": true
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "bridge": {
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ],
      "_inferred": true
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "bridge": {
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ],
      "_inferred": true
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "bridge",
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "bridge": {
      "command": {
        "path": "uvx",
        "args": [
          "MCP-Bridge"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add bridge -- uvx MCP-Bridge

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: MCP-Bridge

Add MCP tools to LibreChat / any OpenAI-compatible chat UI

👤 Self-hosters of OSS chat frontends ⏱ ~30 min intermediate

Когда использовать: You're running LibreChat, Big-AGI, or a custom app that calls /v1/chat/completions and wants tool use, but it doesn't speak MCP.

Предварительные требования

An OpenAI-compatible inference backend — OpenAI, Anthropic-via-proxy, vLLM, Ollama, etc.
At least one MCP server you want to expose — filesystem, fetch, postgres — whatever you've got

Поток

Write config.json

Write me an MCP-Bridge config.json that proxies OpenAI and exposes filesystem MCP (rooted at /data) and fetch MCP.✓ Скопировано

→ Valid config with inference_server and mcp_servers sections
Run via Docker

Give me the docker run command to start MCP-Bridge using this config on port 8000.✓ Скопировано

→ Working docker command with volume mounts
Point the chat UI at the bridge

Show me what API base URL to set in LibreChat to use the bridge instead of OpenAI directly.✓ Скопировано

→ Config pointing to http://localhost:8000/v1

Итог: LibreChat conversations can now call filesystem and fetch tools, transparently.

Подводные камни

Not all OpenAI-compatible clients support tool calls — Verify your UI supports functions in responses before wiring; check its docs for 'tool calling' support
Streaming responses not yet implemented — Disable streaming in the client; use non-streaming endpoints

Сочетать с: filesystem · fetch

Give your own Python/JS agent framework MCP tool access

👤 Devs building custom agents on OpenAI SDK ⏱ ~25 min intermediate

Когда использовать: You're building with the raw OpenAI SDK (or LangChain's OpenAI client) and want to plug in the MCP ecosystem without rewriting the agent.

Поток

Start MCP-Bridge locally

Run MCP-Bridge with upstream set to OpenAI and these MCP servers: [list].✓ Скопировано

→ Bridge listening on :8000
Point OpenAI client base_url at the bridge

Show me Python SDK init: client = OpenAI(base_url='http://localhost:8000/v1', api_key=...). Then call chat completions.✓ Скопировано

→ Code snippet that works unchanged

Итог: Zero-touch tool access for your existing agent code.

Подводные камни

Bridge is a single point of failure — For prod, run with supervisord/systemd and healthcheck endpoint

Комбинации

Сочетайте с другими MCP — эффект x10

bridge + filesystem + fetch

Budget self-hosted ChatGPT replacement with real tool use

Expose filesystem (rooted at ~/Notes) and fetch via MCP-Bridge, then use LibreChat to browse + summarize.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
POST /v1/chat/completions	OpenAI-compatible messages + tools omitted (auto-injected)	Main entrypoint — drop-in for OpenAI	1 LLM call + N tool calls
GET /tools		Discover what's available	free
SSE /bridge		Attach an external MCP client to the bridge over SSE	free

Стоимость и лимиты

Во что обходится

Квота API: Pass-through — whatever your upstream inference provider charges
Токенов на вызов: Bridge adds ~100-500 tokens of tool definitions per request
Деньги: Free (MIT). You pay for your LLM + wherever you host it.
Совет: Only attach MCP servers you need — every attached tool bloats the system prompt.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: Upstream API key + MCP server creds in config.json; lock down file permissions

Исходящий трафик: Requests go to your configured upstream (e.g. OpenAI) + whichever MCP servers

Никогда не давайте: Expose the bridge to the internet without enabling bearer auth

Streaming not implemented — clients that require streaming will fail.
Soft-deprecated in favor of Open WebUI's native MCP (0.6.31+) if you use Open WebUI specifically.

Устранение неполадок

Частые ошибки и исправления

Client says 'tool_use not supported'

Upstream model or client UI doesn't support function calling. Use a model that does (gpt-4o, claude, llama 3.1+).

MCP server connection refused

Check the command in config.json actually runs. Bridge runs it as subprocess; test manually: npx -y the-mcp.

401 from bridge when auth enabled

Set Authorization: Bearer <key> header; the key must be in config under security.auth.keys.

Альтернативы

MCP-Bridge в сравнении

Альтернатива	Когда использовать	Компромисс
Open WebUI native MCP	You specifically use Open WebUI 0.6.31+	Built-in — no bridge needed, but Open WebUI only
LiteLLM with custom callbacks	You want multi-provider routing + tool injection	More complex; LiteLLM doesn't natively speak MCP either
mcpo	You want to expose MCP tools as plain OpenAPI for non-LLM clients too	Different shape — OpenAPI-first rather than chat-completions-first

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills