Postgres Query MCP
A read-only PostgreSQL MCP server that translates natural language queries into SQL, enforcing database routing, table/column whitelists, and safety checks. It offers schema inspection and query tools with optional output as SQL or results.
README
Postgres Query MCP
一个面向本地开发的、只读 PostgreSQL MCP Server。它把自然语言转换为 SQL，并在服务端强制执行数据库路由、表列白名单、危险 SQL 拦截、执行前 EXPLAIN、超时和限流。
快速开始
cp .env.example .env
uv sync --all-groups
uv run python -m pgmcp.main
默认策略已连接到本机正在运行的 Postgres 15.18：
postgresql://postgres:postgres@127.0.0.1:5432/db_query_demo
它包含 users 和 orders 表。服务层会拦截写操作及 users.email；在生产环境应改用独立只读账号。若需要启动仓库自带的隔离演示数据库，执行 docker compose up -d，再将连接串改为 postgresql://pgmcp_reader:pgmcp_reader@127.0.0.1:5433/db_query_demo。
配置 MCP 客户端时，使用：
{
"mcpServers": {
"postgres-query": {
"command": "uv",
"args": ["run", "python", "-m", "pgmcp.main"],
"cwd": "/absolute/path/to/pgmcp"
}
}
}
未设置 PGMCP_OPENAI_API_KEY 时，服务仍可启动和提供 Schema 工具；调用 query 会返回明确的配置错误。服务兼容 OpenAI 格式的 API。使用 DeepSeek 时，在 MCP 环境变量中设置：
PGMCP_OPENAI_API_KEY=<你的 DeepSeek API Key>
PGMCP_OPENAI_BASE_URL=https://api.deepseek.com
PGMCP_OPENAI_MODEL=deepseek-v4-flash
MCP 工具
list_databases：可查询数据库列表。describe_table：读取受允许的表结构。refresh_schema：刷新目标数据库的内存 Schema 缓存。query：自然语言查询，output_mode可选sql或result。
验证
uv run pytest
uv run ruff check .
Prometheus 指标默认暴露在 http://127.0.0.1:9464/metrics。详细范围和阶段说明见 项目计划。
多数据库端到端测试
隔离 Docker 环境会创建 db_query_demo 和 reporting_demo 两个数据库。它们使用同一个只读角色，但策略允许访问的表完全不同。
docker compose up -d
PGMCP_RUN_INTEGRATION=1 uv run pytest -m integration -q
测试会验证两个数据库的正常查询、跨库对象访问被拒绝，以及未知数据库被拒绝；固定 SQL 生成器让这些测试不依赖 OpenAI API Key。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.