MCP.so
ログイン

Langgraph-MCP Client for Postgresql Example

@BrianCusack

基本情報

カテゴリ

推論

トランスポート

stdio

作者

BrianCusack

Langgraph-MCP Client for Postgresql Example について

LangGraph implementation interacting with a PostgreSQL MCP Server

Langgraph-MCP Client for Postgresql Example の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "LangGraph-MCP-Client": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Langgraph-MCP Client for Postgresql Example のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Langgraph-MCP Client for Postgresql Example?

This repository demonstrates a low-level example of how to interact with an MCP server as a Docker image, connected to a PostgreSQL database for LangGraph agents. It is intended for developers who want to integrate PostgreSQL data sources with LangGraph using the Model Context Protocol (MCP).

How to use Langgraph-MCP Client for Postgresql Example?

Clone the repository, create a .env file with database credentials (DB_HOST, DB_PORT, DB_USER, DB_PASSWORD, DB_NAME), install the UV package globally, and build the MCP Postgres Docker image. Then run uv sync followed by uv run queryagent to start the query agent, optionally passing a natural language query as an argument (e.g., uv run queryagent "Who holds the most funds in their account?").

Key features of Langgraph-MCP Client for Postgresql Example

  • Connects to a PostgreSQL database via an MCP server.
  • Uses langchain_mcp_adapters.tools.load_mcp_tools to create MCP tools.
  • Employs LangGraph's create_react_agent for fast agent templating.
  • Outputs the agent’s stream to a file.
  • Accepts user queries via command line.

Use cases of Langgraph-MCP Client for Postgresql Example

  • Querying a banking database using natural language questions.
  • Learning how to integrate a PostgreSQL MCP server with LangGraph agents.
  • Prototyping a LangGraph agent that uses database tools over MCP.

よくある質問

1

What are the prerequisites for running this project?

You need Docker, a running PostgreSQL database, and the MCP Servers repository (to build the Postgres MCP image). The UV package manager must also be installed globally.

2

How do I set up the database connection?

Create a `.env` file in the repository root with the variables `DB_HOST`, `DB_PORT`, `DB_USER`, `DB_PASSWORD`, and `DB_NAME`, replacing placeholders with your actual credentials.

3

What should I do if I encounter UV package errors?

Ensure the UV CLI is installed globally and that the `uv sync` command completes without errors.

4

How do I build the PostgreSQL MCP Server Docker image?

Clone the MCP Servers repository, navigate to its directory, and run `docker build -t mcp/postgres -f src/postgres/Dockerfile .`

5

How can I run the query agent with a specific question?

Run `uv run queryagent "your question"` from the project directory, replacing `"your question"` with the desired natural language query.

コメント

「推論」の他のコンテンツ