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.
@BrianCusack
基本情報
LangGraph implementation interacting with a PostgreSQL MCP Server
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"
]
}
}
}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。
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).
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?").
langchain_mcp_adapters.tools.load_mcp_tools to create MCP tools.create_react_agent for fast agent templating.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.
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.
Ensure the UV CLI is installed globally and that the `uv sync` command completes without errors.
Clone the MCP Servers repository, navigate to its directory, and run `docker build -t mcp/postgres -f src/postgres/Dockerfile .`
Run `uv run queryagent "your question"` from the project directory, replacing `"your question"` with the desired natural language query.
MCP server that gives Claude persistent project memory — roadmap, session history, and codebase context. Type continue and Claude picks up exactly where you left off
Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.
Multi-Agent AI Orchestration Workshop
emergency-medicare-planner-mcp-server
This is a very basic implementation of an Mcp-Reasoning-Server for Cursor AI .
コメント