langsmith-fetch-skill MCP — 使用场景, 安装 & 实时演示

为什么要用

核心特性

Pulls traces directly from LangSmith Studio via CLI
Auto-triggers on debugging-flavored prompts
Tracks failures + root causes
Latency + token usage analysis
Tool-call and memory operation review
Session export

实时演示

实际使用效果

langsmith-fetch-skill.replay ▶ 就绪

0/0

安装

选择你的客户端

~/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
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.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 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

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
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "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
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.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 使用服务器对象数组，而非映射。

~/.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"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

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

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： langsmith-fetch-skill

Diagnose a slow agent without opening LangSmith UI

👤 LangChain/LangGraph devs ⏱ ~20 min intermediate

何时使用： An agent that used to be snappy is now slow; you want root cause.

前置条件

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

步骤

Ask Claude to diagnose

Why is my agent <name> slow? Pull the last 20 traces from LangSmith and find the hotspot.✓ 已复制

→ Skill fetches traces; reports latency by step
Drill in

Focus on trace <id> — break down tool-call times.✓ 已复制

→ Per-tool latency with the outlier called out

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

注意事项

Optimizing the average when tail latency is the problem — Ask for p95/p99 specifically

搭配使用： filesystem

Root-cause an agent failure from a trace id

👤 Anyone running LangGraph in production ⏱ ~15 min intermediate

何时使用： A user reported an error; you have the trace id.

步骤

Fetch + analyze

Debug trace <id>. What was the immediate error, what's the root cause in the graph?✓ 已复制

→ Error step + upstream decision that led to it

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

Find which node burns the most tokens

👤 Teams optimizing LLM spend ⏱ ~30 min intermediate

何时使用： Monthly review of agent spend.

步骤

Aggregate token usage

Across last 7 days' traces, rank graph nodes by total token usage.✓ 已复制

→ Ranked table with % share
Propose tightening

For the top 3, propose prompt-compression or model downgrade options.✓ 已复制

→ Targeted opt list

结果： Measurable spend reduction without chasing tiny savings.

组合

与其他 MCP 搭配，撬动十倍杠杆

langsmith-fetch-skill + filesystem

Save exports alongside the agent code for lineage

Export the debugging session to debugging/traces/<date>.json.✓ 已复制

langsmith-fetch-skill + github

Attach trace summary to a bug report

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

工具

此 MCP 暴露的能力

工具	输入参数	何时调用	成本
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

成本与限制

运行它的成本

API 配额: LangSmith: depends on plan; Studio has generous quotas
每次调用 Token 数: Low — traces are structured
费用: Free skill; LangSmith free tier covers most devs
提示: Use fetch_recent with a narrow window, not full history

安全

权限、密钥、影响范围

最小权限： LangSmith: read on your project(s)

凭据存储： LANGCHAIN_API_KEY in env

数据出站： Only to LangSmith (where the traces already live)

切勿授予： Write to LangSmith — skill only reads

Traces can include user inputs and outputs — treat them as user data under your privacy policy.

故障排查

常见错误与修复

langsmith-fetch: command not found

Install LangSmith CLI or ensure it's on PATH

验证： which langsmith-fetch

Empty results

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

替代方案

langsmith-fetch-skill 对比其他方案

替代方案	何时用它替代	权衡
LangSmith web UI	You prefer clicking	No Claude analysis

langsmith-fetch-skill