MCP-Bridge MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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

Live-Demo

In der Praxis

bridge.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

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

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

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

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

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

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

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

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

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add bridge -- uvx MCP-Bridge

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: MCP-Bridge

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

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

Wann einsetzen: 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.

Voraussetzungen

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

Ablauf

Write config.json

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

→ 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.✓ Kopiert

→ 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.✓ Kopiert

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

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

Fallstricke

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

Kombinieren mit: filesystem · fetch

Give your own Python/JS agent framework MCP tool access

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

Wann einsetzen: 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.

Ablauf

Start MCP-Bridge locally

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

→ 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.✓ Kopiert

→ Code snippet that works unchanged

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

Fallstricke

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

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

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.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
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

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Pass-through — whatever your upstream inference provider charges
Tokens pro Aufruf: Bridge adds ~100-500 tokens of tool definitions per request
Kosten in €: Free (MIT). You pay for your LLM + wherever you host it.
Tipp: Only attach MCP servers you need — every attached tool bloats the system prompt.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Upstream API key + MCP server creds in config.json; lock down file permissions

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

Niemals gewähren: 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.

Fehlerbehebung

Häufige Fehler und Lösungen

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.

Alternativen

MCP-Bridge vs. andere

Alternative	Wann stattdessen	Kompromiss
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

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen