MetaMCP MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

Aggregate N MCP servers → one namespaced endpoint
Multiple transports: SSE, Streamable HTTP, OpenAPI
Auth: API keys, OAuth 2.1 (MCP 2025-06-18 spec), Better Auth, OIDC SSO
Rate limits per endpoint and per user; tool overrides and renaming
Inspector UI for debugging tool calls without a real client
Docker Compose self-host in ~5 minutes

Live-Demo

In der Praxis

metamcp.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": {
    "metamcp": {
      "command": "uvx",
      "args": [
        "mcp-proxy",
        "http://localhost:12008/metamcp/default/sse"
      ],
      "env": {
        "API_ACCESS_TOKEN": "mm_..."
      }
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "metamcp": {
      "command": "uvx",
      "args": [
        "mcp-proxy",
        "http://localhost:12008/metamcp/default/sse"
      ],
      "env": {
        "API_ACCESS_TOKEN": "mm_..."
      }
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "metamcp": {
      "command": "uvx",
      "args": [
        "mcp-proxy",
        "http://localhost:12008/metamcp/default/sse"
      ],
      "env": {
        "API_ACCESS_TOKEN": "mm_..."
      }
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "metamcp": {
      "command": "uvx",
      "args": [
        "mcp-proxy",
        "http://localhost:12008/metamcp/default/sse"
      ],
      "env": {
        "API_ACCESS_TOKEN": "mm_..."
      }
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "metamcp",
      "command": "uvx",
      "args": [
        "mcp-proxy",
        "http://localhost:12008/metamcp/default/sse"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "metamcp": {
      "command": {
        "path": "uvx",
        "args": [
          "mcp-proxy",
          "http://localhost:12008/metamcp/default/sse"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add metamcp -- uvx mcp-proxy http://localhost:12008/metamcp/default/sse

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

Anwendungsfälle

Praxisnahe Nutzung: MetaMCP

Give a team one MCP URL instead of 15 per-laptop configs

👤 Platform teams rolling out Claude Desktop / Cursor org-wide ⏱ ~45 min intermediate

Wann einsetzen: Your team wants filesystem, github, postgres, sentry, slack, notion all available — but you don't want every engineer maintaining 6 tokens in JSON files that leak.

Voraussetzungen

A server that runs Docker — Any Linux box / VM with Docker Compose; ~1 CPU / 1GB RAM is plenty
Upstream credentials stored server-side — Put GITHUB_TOKEN, DB_URL, etc. in MetaMCP's .env — they never reach laptops

Ablauf

Bring up MetaMCP

git clone github.com/metatool-ai/metamcp && cp example.env .env && docker compose up -d✓ Kopiert

→ Admin UI reachable at http://host:12008; default login works
Register upstream servers

In the MetaMCP admin UI, add filesystem, github, postgres, notion as namespaces 'fs', 'gh', 'db', 'notion'.✓ Kopiert

→ Each appears in the endpoint's tool list with prefix
Give the team one config

Publish the Claude Desktop config snippet — one mcp-proxy entry pointing at /metamcp/team-default/sse — to internal docs.✓ Kopiert

→ Every engineer paste-and-goes

Ergebnis: New hires onboard in 90 seconds; token rotation happens once, server-side.

Fallstricke

Claude Desktop can't do SSE natively — Use mcp-proxy (uvx mcp-proxy <sse-url>) on the client side — MetaMCP docs include this snippet
Namespaces collide or are ugly — Rename tools in MetaMCP's override UI; e.g. 'fs.read_text_file' → 'repo.read'

Kombinieren mit: filesystem · github · postgres

Audit which MCP tools your agents actually call — and throttle the noisy ones

👤 Security / platform engineers ⏱ ~20 min intermediate

Wann einsetzen: You need to know what tools are invoked, how often, and which user. Per-server rate limits are not enough — you want aggregate visibility.

Ablauf

Turn on request logs

In MetaMCP settings, enable per-request logging and endpoint-level rate limits (e.g. 10 req/s per user).✓ Kopiert

→ Logs appear in the admin UI
Replay a suspicious trace

Pull the last hour of tool calls for user 'marketing-bot'. Anything hitting the github write tools?✓ Kopiert

→ Tabular audit; write calls highlighted
Throttle abusive tools

Set 'notion.create_page' to 1 req/min for the 'marketing-bot' endpoint. Apply now.✓ Kopiert

→ Rate limit visible in config; takes effect immediately

Ergebnis: Governance surface without writing custom middleware.

Route dev/staging/prod MCP traffic through one gateway

👤 Teams with environment-specific credentials ⏱ ~30 min advanced

Wann einsetzen: You want the same Claude Desktop config to hit staging-postgres at work and prod-postgres only with an explicit flag — no editing JSON.

Ablauf

Create endpoints

Create 3 MetaMCP endpoints: /dev, /staging, /prod. Wire each to the right upstream credentials.✓ Kopiert

→ Three endpoint URLs
Per-endpoint auth

Give prod its own API key and enable OIDC SSO for that endpoint only.✓ Kopiert

→ dev/staging open with shared key, prod behind SSO
Test via inspector

Use MetaMCP's inspector UI: call a read-only query through /prod as yourself; confirm auth works.✓ Kopiert

→ Successful tool call in the inspector

Ergebnis: Accident-proof environment switching.

Kombinieren mit: postgres

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

metamcp + filesystem + github + postgres

Hide the per-tool sprawl behind one gateway URL

Configure MetaMCP with fs, gh, db namespaces; point Claude Desktop at the gateway; stop pasting tokens into JSON.✓ Kopiert

metamcp + claude-desktop

Claude Desktop speaks stdio, MetaMCP speaks SSE — use mcp-proxy as the bridge

In claude_desktop_config.json, wrap MetaMCP's SSE URL with uvx mcp-proxy.✓ Kopiert

metamcp + sentry

Send MetaMCP request logs/errors into Sentry for alerting

Wire MetaMCP's OpenTelemetry/logs into Sentry; alert on 5xx rate > 1%.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
(dynamic)	Depends on which MCP servers you've registered — tools are forwarded with a namespace prefix	Any time — it's a transparent proxy with auth + rate-limit added	free (local gateway + upstream's own cost)

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: None — self-hosted
Tokens pro Aufruf: Same as upstream tools; MetaMCP adds ~1–3ms of proxy latency
Kosten in €: Free (MIT); you pay for the VM
Tipp: One small VPS ($5/mo) runs MetaMCP + a couple upstream servers; no need for Kubernetes until traffic > 100 req/s

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: MetaMCP .env holds all upstream credentials; clients never see them

Datenabfluss: Only to the upstream MCPs you've registered. Nothing phones home.

Niemals gewähren: Expose the admin UI to the public internet without SSO or auth proxy

The default Docker Compose binds 12008 to 0.0.0.0 — put MetaMCP behind Tailscale, Cloudflare Tunnel, or a reverse proxy with TLS before exposing it to teammates.
Tokens in .env are plain text. Mount a secrets provider (1Password CLI, Vault) for prod.

Fehlerbehebung

Häufige Fehler und Lösungen

Claude Desktop shows 'server failed to start'

Claude Desktop uses stdio, not SSE. Configure with uvx mcp-proxy http://host:12008/metamcp/<endpoint>/sse, not a direct URL.

Prüfen: Try the same URL in MetaMCP's inspector first — if it works there, the issue is stdio-to-SSE bridging

Tools missing or not namespaced

Check the endpoint config — namespaces are per-endpoint, not global. Re-sync tool discovery after adding an upstream.

Prüfen: In admin UI, click 'Re-sync tools' on the endpoint

401 at the gateway

API_ACCESS_TOKEN env must match the endpoint's API key; OAuth endpoints need a completed consent flow first.

Prüfen: curl -H 'Authorization: Bearer $TOKEN' http://host:12008/metamcp/<ep>/mcp

Upstream MCP server keeps restarting

Check the upstream container's logs via docker logs; MetaMCP will mark it unhealthy and surface errors to clients.

Prüfen: docker compose logs <upstream>

Alternativen

MetaMCP vs. andere

Alternative	Wann stattdessen	Kompromiss
IBM mcp-context-forge	Enterprise deployment with stronger IAM/governance needs	Heavier stack; more config surface
mcp-use/mcp-use	You want a framework to build AI agents + servers, not just a proxy	More code; more surface; more power
Direct per-client configs	You run ≤3 MCPs and don't share configs with anyone	No governance, no auth, tokens on every laptop

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen