MCP-Bridge MCP — Casos de uso, Instalar & Demo en vivo

Por qué usarlo

Características clave

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

Demo en vivo

Cómo se ve en la práctica

bridge.replay ▶ listo

0/0

Instalar

Elige tu cliente

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

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

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

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

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

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

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

claude mcp add bridge -- uvx MCP-Bridge

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: MCP-Bridge

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

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

Cuándo usarlo: 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.

Requisitos previos

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

Flujo

Write config.json

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

→ 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.✓ Copiado

→ 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.✓ Copiado

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

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

Errores comunes

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

Combinar con: filesystem · fetch

Give your own Python/JS agent framework MCP tool access

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

Cuándo usarlo: 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.

Flujo

Start MCP-Bridge locally

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

→ 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.✓ Copiado

→ Code snippet that works unchanged

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

Errores comunes

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

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

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.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
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

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: Pass-through — whatever your upstream inference provider charges
Tokens por llamada: Bridge adds ~100-500 tokens of tool definitions per request
Monetario: Free (MIT). You pay for your LLM + wherever you host it.
Consejo: Only attach MCP servers you need — every attached tool bloats the system prompt.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: Upstream API key + MCP server creds in config.json; lock down file permissions

Salida de datos: Requests go to your configured upstream (e.g. OpenAI) + whichever MCP servers

No conceder nunca: 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.

Resolución de problemas

Errores comunes y soluciones

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.

Alternativas

MCP-Bridge vs otros

Alternativa	Cuándo usarla	Contrapartida
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

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills