mcp-agent-langchainjs MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

LangChain.js agent with MCP tool integration (reference pattern)
Serverless deploy — Static Web Apps + Azure Functions + Cosmos DB
IaC via Bicep templates
User auth + session history
Local dev via Ollama or Codespaces; production via azd up

Живое демо

Как выглядит на практике

agent-langchainjs.replay ▶ готово

0/0

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "agent-langchainjs": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-agent-langchainjs"
      ],
      "_inferred": true
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "agent-langchainjs": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-agent-langchainjs"
      ],
      "_inferred": true
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "agent-langchainjs": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-agent-langchainjs"
      ],
      "_inferred": true
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "agent-langchainjs": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-agent-langchainjs"
      ],
      "_inferred": true
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "agent-langchainjs",
      "command": "npx",
      "args": [
        "-y",
        "mcp-agent-langchainjs"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "agent-langchainjs": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-agent-langchainjs"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add agent-langchainjs -- npx -y mcp-agent-langchainjs

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: mcp-agent-langchainjs

Bootstrap a serverless agent on Azure with MCP tool calls

👤 Azure devs building AI features ⏱ ~120 min advanced

Когда использовать: You want to ship an LLM-powered feature on Azure and need a working reference to fork.

Предварительные требования

Azure subscription — azure.microsoft.com — free tier covers dev
Azure Developer CLI — brew install azd or Windows installer

Поток

Fork and deploy

Fork Azure-Samples/mcp-agent-langchainjs and walk me through azd up to deploy to my Azure sub.✓ Скопировано

→ Live Azure URL + Functions + Cosmos provisioned
Swap the demo tool

Replace the burger-ordering MCP with a custom MCP for my domain (e.g. appointment booking). Show me the wiring.✓ Скопировано

→ Code diff + working custom tool
Customize the UI

The sample has a chat UI; customize brand/colors and the welcome message.✓ Скопировано

→ Styled app

Итог: A shippable Azure-hosted agent derived from a vetted sample.

Подводные камни

Free-tier Azure OpenAI has low quota — Provision your own OpenAI resource in a region with capacity; set endpoint in env
Local Ollama doesn't handle complex tool calls well — Use a cloud model (GPT-4o-mini, etc.) for dev that involves multi-step tool calls

Learn the MCP + LangChain.js integration pattern

👤 Devs new to MCP ⏱ ~60 min intermediate

Когда использовать: You're evaluating MCP and want to see how it plugs into the LangChain.js ecosystem.

Поток

Read the code

Summarize how this repo wires MCP to LangChain.js agents. What's the key integration point?✓ Скопировано

→ Architecture explanation
Run locally

Run it in Codespaces. Exercise the burger-order flow. Observe the MCP tool calls in logs.✓ Скопировано

→ Working local run + tool call traces

Итог: Hands-on understanding of the pattern before building your own.

Комбинации

Сочетайте с другими MCP — эффект x10

agent-langchainjs + github

CI/CD the sample to your own fork

Fork the repo, set up GitHub Actions to azd deploy on push to main.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
(reference app — not a callable MCP)	N/A	This is a sample app you deploy, not a tool Claude calls	N/A

Стоимость и лимиты

Во что обходится

Квота API: Azure consumption-based
Токенов на вызов: N/A — you're building the app, not calling it as a tool
Деньги: Varies — cheap on free tier for dev; production costs depend on traffic
Совет: Use Azure cost alerts early. Cosmos DB can be expensive if mis-provisioned — keep it on serverless tier during dev.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: Azure Key Vault + Managed Identity (set up by the Bicep templates)

Исходящий трафик: Entirely within your Azure sub + chosen LLM endpoint

Sample apps are starting points, not production-ready. Harden auth, rate limiting, and observability before going live.
Keep your OpenAI / LLM keys in Key Vault, not in source code.

Устранение неполадок

Частые ошибки и исправления

azd up fails: no capacity in region

OpenAI capacity varies by region. Try eastus2, swedencentral, or francecentral.

Functions cold-start slowness

Use Premium plan for prod; Consumption is fine for dev but cold-starts stall early chats.

MCP tool call not recognized

Confirm the LangChain.js tool binding is using the MCP client the sample sets up. Check the imports.

Альтернативы

mcp-agent-langchainjs в сравнении

Альтернатива	Когда использовать	Компромисс
Vercel AI SDK starter	You prefer Vercel / Next.js hosting	Different cloud; smaller sample
AWS Bedrock Agents + sample	You're on AWS	Different stack; Bedrock agents aren't MCP-native

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills