inspector MCP — Anwendungsfälle, Installieren & Live-Demo

Name: inspector MCP Server
Author: MCPJam

Warum nutzen

Hauptfunktionen

Full JSON-RPC tracing across host/server
Inline LLM chat while inspecting tool calls and context
Evaluation runs across multiple models
OAuth flow debugging with conformance checks
Workspace sharing, CLI, SDK, and CI/CD integration

Live-Demo

In der Praxis

inspector.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": {
    "inspector": {
      "command": "npx",
      "args": [
        "-y",
        "inspector"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "inspector": {
      "command": "npx",
      "args": [
        "-y",
        "inspector"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "inspector": {
      "command": "npx",
      "args": [
        "-y",
        "inspector"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "inspector": {
      "command": "npx",
      "args": [
        "-y",
        "inspector"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "inspector",
      "command": "npx",
      "args": [
        "-y",
        "inspector"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "inspector": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "inspector"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add inspector -- npx -y inspector

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

Anwendungsfälle

Praxisnahe Nutzung: inspector

How to debug why your MCP tool isn't being called

👤 MCP server developers ⏱ ~15 min intermediate

Wann einsetzen: You wrote a tool, Claude doesn't use it, and you don't know why.

Voraussetzungen

Node — nodejs.org or nvm

Ablauf

Launch Inspector

npx @mcpjam/inspector@latest and open the printed URL.✓ Kopiert

→ UI opens in browser
Connect your server

In the UI, add your server (stdio or HTTP) and connect.✓ Kopiert

→ Tools list populates
Simulate a prompt

In the Chat tab, ask a question that should trigger your tool. Watch the JSON-RPC trace.✓ Kopiert

→ Either tool fires (good) or you see why the model rejected it (bad description, missing input schema)

Ergebnis: Concrete reason (wrong tool description, schema issue, model choice) with a visible fix.

Fallstricke

Testing with a weaker model that never uses tools — Test across multiple models in the Evals tab — Haiku, Sonnet, GPT-4o — behavior varies

How to run eval tests on PRs for your MCP server

👤 Teams maintaining production MCPs ⏱ ~30 min advanced

Wann einsetzen: You want to catch 'oops that prompt no longer picks my tool' in CI.

Ablauf

Author evals

In Inspector, create eval cases: (prompt, expected_tool_called, expected_args).✓ Kopiert

→ Eval suite saved
Wire into CI

Use the CLI to run evals on every PR; fail the build on regression.✓ Kopiert

→ .github/workflows/mcp-eval.yml runs evals

Ergebnis: PRs that break tool selection don't merge.

Fallstricke

Evals are flaky when temperature > 0 — Use temperature 0 in eval runs

Kombinieren mit: github

How to diagnose a broken OAuth flow on your MCP server

👤 MCP server devs shipping OAuth-protected tools ⏱ ~20 min advanced

Wann einsetzen: Tokens aren't refreshing, or redirect returns 400.

Ablauf

Enable OAuth debug in Inspector

Configure your server's OAuth endpoints and click 'Test flow'.✓ Kopiert

→ Step-by-step trace of authorize, token, refresh
Identify the break

Inspector highlights nonconforming steps (wrong content-type, missing PKCE, bad scope).✓ Kopiert

→ Specific failure node

Ergebnis: Conforming OAuth implementation.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

inspector + github

Run Inspector evals in a GitHub Action on PRs for your MCP server

Set up a GitHub Action using @mcpjam/inspector CLI to run evals on every PR touching src/tools/.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
(inspector app) connect-server	transport: stdio\|http, command or url	First step	free
(inspector app) execute-tool	tool, args	Manual testing	depends on tool
(inspector app) chat-and-inspect	model, prompt	End-to-end simulation	1 LLM call
(inspector app) run-evals	suite_id	CI regression testing	N LLM calls

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Your LLM/eval keys determine the budget
Tokens pro Aufruf: Evals can burn tokens — limit concurrency + size
Kosten in €: Inspector itself is free. Hosted app at app.mcpjam.com has tiers.
Tipp: Run evals on Haiku for cheap smoke tests; reserve Sonnet/Opus for nightly runs.

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: Whatever scopes your MCP server needs LLM provider keys for evals

Credential-Speicherung: Local env for CLI; workspace secrets for the hosted app

Datenabfluss: Tool calls stay between your MCP and LLM; hosted app stores eval results in your workspace

Niemals gewähren: Don't upload production OAuth client secrets to the hosted app without review

Inspector can call write tools during eval runs — use a sandbox server, not production.

Fehlerbehebung

Häufige Fehler und Lösungen

Can't connect to my stdio server

Make sure the command Inspector runs matches what Claude Desktop runs — working dir and env vars included.

Chat tab says 'model not configured'

Add your Anthropic/OpenAI key in Settings.

Evals pass locally, fail in CI

Env mismatch — pin the same model + temperature in CI as locally.

OAuth test reports 'state mismatch'

Your server isn't preserving the state param; compare to the spec in Inspector's conformance report.

Alternativen

inspector vs. andere

Alternative	Wann stattdessen	Kompromiss
@modelcontextprotocol/inspector (official)	You want the first-party reference inspector	Smaller feature surface; no evals/CI
mcp-client-for-ollama	You want a terminal-only Ollama-backed client	Not a debugger, just a client

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen