MetaMCP MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

metamcp.replay ▶ prêt

0/0

Installer

Choisissez votre 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_..."
      }
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.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 utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la 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_..."
      }
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "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_..."
      }
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : 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

Quand l'utiliser : 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.

Prérequis

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

Déroulement

Bring up MetaMCP

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

→ 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'.✓ Copié

→ 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.✓ Copié

→ Every engineer paste-and-goes

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

Pièges

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'

Combiner avec : filesystem · github · postgres

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

👤 Security / platform engineers ⏱ ~20 min intermediate

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

Déroulement

Turn on request logs

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

→ 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?✓ Copié

→ Tabular audit; write calls highlighted
Throttle abusive tools

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

→ Rate limit visible in config; takes effect immediately

Résultat : Governance surface without writing custom middleware.

Route dev/staging/prod MCP traffic through one gateway

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

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

Déroulement

Create endpoints

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

→ Three endpoint URLs
Per-endpoint auth

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

→ 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.✓ Copié

→ Successful tool call in the inspector

Résultat : Accident-proof environment switching.

Combiner avec : postgres

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

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.✓ Copié

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.✓ Copié

metamcp + sentry

Send MetaMCP request logs/errors into Sentry for alerting

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
(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)

Coût et limites

Coût d'exécution

Quota d'API: None — self-hosted
Tokens par appel: Same as upstream tools; MetaMCP adds ~1–3ms of proxy latency
Monétaire: Free (MIT); you pay for the VM
Astuce: One small VPS ($5/mo) runs MetaMCP + a couple upstream servers; no need for Kubernetes until traffic > 100 req/s

Sécurité

Permissions, secrets, portée

Stockage des identifiants : MetaMCP .env holds all upstream credentials; clients never see them

Sortie de données : Only to the upstream MCPs you've registered. Nothing phones home.

Ne jamais accorder : 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.

Dépannage

Erreurs courantes et correctifs

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.

Vérifier : 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.

Vérifier : 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.

Vérifier : 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.

Vérifier : docker compose logs <upstream>

Alternatives

MetaMCP vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills