PostgreSQL MCP 服务器

Created By
cynhardchuengca year ago
Overview

What is pg-mcp-server?

pg-mcp-server is a PostgreSQL database access server based on the Model Context Protocol (MCP) that allows AI assistants to securely perform PostgreSQL database operations, including querying, inserting, updating, and deleting data, as well as managing table structures.

How to use pg-mcp-server?

To use pg-mcp-server, clone the repository, install dependencies, compile the TypeScript code, configure the MCP settings, and run the server with the appropriate PostgreSQL connection string.

Key features of pg-mcp-server?

  • Secure access to PostgreSQL database operations via AI assistants.
  • Support for various database operations including SQL queries, data modifications, and transaction management.
  • Easy integration with AI systems using the MCP SDK.

Use cases of pg-mcp-server?

  1. Allowing AI assistants to execute read-only SQL queries.
  2. Enabling AI to perform data modifications with user confirmation.
  3. Managing database transactions and ensuring data integrity.

FAQ from pg-mcp-server?

  • Can pg-mcp-server handle all types of SQL operations?

Yes! It supports a wide range of SQL operations including SELECT, INSERT, UPDATE, and DELETE.

  • Is pg-mcp-server secure for production use?

Yes! It is designed with security in mind, but ensure proper database user permissions and configurations are set.

  • How do I configure the server?

Configuration is done through environment variables and a JSON file for MCP settings.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
cynhardchuengc
Star
0
Language
TypeScript
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago