/ Verzeichnis / Playground / langsmith-fetch-skill
● Community OthmanAdi ⚡ Sofort

langsmith-fetch-skill

von OthmanAdi · OthmanAdi/langsmith-fetch-skill

Debug LangChain / LangGraph agents from your terminal — fetches LangSmith Studio traces into Claude Code and analyzes failures, latency, tool calls.

A focused observability skill. When you ask Claude to debug an agent, it runs langsmith-fetch against LangSmith Studio, pulls trace data, analyzes execution patterns, and surfaces failures, root causes, latency hotspots, and tool-call issues. Export sessions for later review.

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

langsmith-fetch-skill.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": {
    "langsmith-fetch-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OthmanAdi/langsmith-fetch-skill",
        "~/.claude/skills/langsmith-fetch-skill"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "langsmith-fetch-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OthmanAdi/langsmith-fetch-skill",
        "~/.claude/skills/langsmith-fetch-skill"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "langsmith-fetch-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OthmanAdi/langsmith-fetch-skill",
        "~/.claude/skills/langsmith-fetch-skill"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "langsmith-fetch-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OthmanAdi/langsmith-fetch-skill",
        "~/.claude/skills/langsmith-fetch-skill"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "langsmith-fetch-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OthmanAdi/langsmith-fetch-skill",
        "~/.claude/skills/langsmith-fetch-skill"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json
{
  "context_servers": {
    "langsmith-fetch-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/OthmanAdi/langsmith-fetch-skill",
          "~/.claude/skills/langsmith-fetch-skill"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add langsmith-fetch-skill -- git clone https://github.com/OthmanAdi/langsmith-fetch-skill ~/.claude/skills/langsmith-fetch-skill

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

Anwendungsfälle

Praxisnahe Nutzung: langsmith-fetch-skill

Diagnose a slow agent without opening LangSmith UI

👤 LangChain/LangGraph devs ⏱ ~20 min intermediate

Wann einsetzen: An agent that used to be snappy is now slow; you want root cause.

Voraussetzungen
  • LangSmith API key — smith.langchain.com -> Settings -> API Keys
  • Skill installed — git clone https://github.com/OthmanAdi/langsmith-fetch-skill ~/.claude/skills/langsmith-fetch-skill
Ablauf
  1. Ask Claude to diagnose
    Why is my agent <name> slow? Pull the last 20 traces from LangSmith and find the hotspot.✓ Kopiert
    → Skill fetches traces; reports latency by step
  2. Drill in
    Focus on trace <id> — break down tool-call times.✓ Kopiert
    → Per-tool latency with the outlier called out

Ergebnis: A specific step to optimize, not a hunch.

Fallstricke
  • Optimizing the average when tail latency is the problem — Ask for p95/p99 specifically
Kombinieren mit: filesystem

Root-cause an agent failure from a trace id

👤 Anyone running LangGraph in production ⏱ ~15 min intermediate

Wann einsetzen: A user reported an error; you have the trace id.

Ablauf
  1. Fetch + analyze
    Debug trace <id>. What was the immediate error, what's the root cause in the graph?✓ Kopiert
    → Error step + upstream decision that led to it

Ergebnis: A fix targeting the actual decision point, not the symptom.

Find which node burns the most tokens

👤 Teams optimizing LLM spend ⏱ ~30 min intermediate

Wann einsetzen: Monthly review of agent spend.

Ablauf
  1. Aggregate token usage
    Across last 7 days' traces, rank graph nodes by total token usage.✓ Kopiert
    → Ranked table with % share
  2. Propose tightening
    For the top 3, propose prompt-compression or model downgrade options.✓ Kopiert
    → Targeted opt list

Ergebnis: Measurable spend reduction without chasing tiny savings.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

langsmith-fetch-skill + filesystem

Save exports alongside the agent code for lineage

Export the debugging session to debugging/traces/<date>.json.✓ Kopiert
langsmith-fetch-skill + github

Attach trace summary to a bug report

Summarize trace <id> and post as comment on GitHub issue #42.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
fetch_recent project, limit Broad diagnosis LangSmith quota
fetch_trace trace_id Deep dive on one run LangSmith quota
analyze_failures traces Post-fetch analysis 0
export_session traces Archive for later 0

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
LangSmith: depends on plan; Studio has generous quotas
Tokens pro Aufruf
Low — traces are structured
Kosten in €
Free skill; LangSmith free tier covers most devs
Tipp
Use fetch_recent with a narrow window, not full history

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: LangSmith: read on your project(s)
Credential-Speicherung: LANGCHAIN_API_KEY in env
Datenabfluss: Only to LangSmith (where the traces already live)
Niemals gewähren: Write to LangSmith — skill only reads

Fehlerbehebung

Häufige Fehler und Lösungen

langsmith-fetch: command not found

Install LangSmith CLI or ensure it's on PATH

Prüfen: which langsmith-fetch
Empty results

Check project name and time window; traces are project-scoped

Alternativen

langsmith-fetch-skill vs. andere

AlternativeWann stattdessenKompromiss
LangSmith web UIYou prefer clickingNo Claude analysis

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen