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

Por que usar

Principais recursos

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 ao vivo

Como fica na prática

bridge.replay ▶ pronto

0/0

Instalar

Escolha seu 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
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

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

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

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

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

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

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add bridge -- uvx MCP-Bridge

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: MCP-Bridge

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

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

Quando usar: 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.

Pré-requisitos

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

Fluxo

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.

Armadilhas

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

Combine com: filesystem · fetch

Give your own Python/JS agent framework MCP tool access

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

Quando usar: 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.

Fluxo

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.

Armadilhas

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

Combinações

Combine com outros MCPs para 10× de alavancagem

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

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
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

Custo e limites

O que custa rodar

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

Segurança

Permissões, segredos, alcance

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

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

Nunca conceda: 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.

Solução de problemas

Erros comuns e correções

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. outros

Alternativa	Quando usar	Troca
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

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills