"A GitHub repository for agent guardrails" matching MCP servers:

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

Gives Claude control of a real, headed Chromium browser via Playwright, enabling web navigation, clicking, typing, screenshots, and JavaScript evaluation.

Automatically crawls documentation websites, converts them to organized markdown files, and generates condensed cheat sheets. Intelligently categorizes content into tools/APIs and provides local-first access to downloaded documentation.

Provides an MCP server for scraping and retrieving data from GitHub Projects, including issues, pull requests, and organizational metadata. It enables natural language interaction with project boards and repository contents using GitHub Personal Access Tokens.

An Operit-compatible adapter of the Exa MCP server, enabling web search, code search, and company research capabilities in AI assistants. It fixes MCP handshake compatibility issues, allowing tools like web_search_exa and web_fetch_exa to load and run reliably.

Scans any website to generate an Agent Readiness Report based on the ASO framework, evaluating agent discoverability, trust, interoperability, and commerce readiness.

MCP server that gives AI agents browser-based access to Mobbin for design research, screen discovery, and screenshot collection through automated browser control.

这是一个面向中文圈的MCP服务器，将中国互联网常用能力（如地图、快递、RSS、B站等）封装为标准MCP工具，方便AI Agent安全调用。

A Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.

Enables AI assistants to fetch, search, and organize menu information from For Five Coffee café. Provides access to complete menu data, category filtering, and item search capabilities through both MCP and REST API interfaces.

Enables AI agents to drive real Google Chrome with stealth and captcha handling, using Patchright to avoid bot detection.

MCP server that reads Korean school class and teacher timetables from Comci's public schedules, detects schedule changes, and exposes structured data via CLI, local REST, and MCP stdio.

A browser research MCP server that emphasizes evidence-centric workflows, secure browser automation, and deterministic data extraction, with structured responses and artifact-based screenshots.

A hardened local browser MCP server that drives your existing Chrome over the DevTools Protocol, providing token-efficient Markdown extraction and stealth features to avoid trivial automation detection.

A self-hosted MCP server that collects links and articles from web and mobile, allowing AI agents like Claude or ChatGPT to read and analyze them as a reading list.

Provides a headless Chromium browser through MCP, enabling AI agents to browse JavaScript-rendered pages, search the web, capture screenshots, extract tables and data, and run stateful multi-step interactions like clicking, typing, and form submission.

MCP server that gives AI agents video parsing and downloading capabilities, offering tools to extract video info, list formats, and download videos from sites like Bilibili and YouTube via yt-dlp.

MCP server that wraps Playwright to give AI agents eyes on the web, enabling browser search, navigation, extraction, and interaction with intelligent LLM-based DOM extraction and skill caching.

Bridges UI feedback captured by a browser extension on localhost apps into a Claude Code session, queueing picked elements, comments and rewrite requests as batches that the coding agent can claim and act on. It also lets Claude report progress and per-item results back to the extension, and can import batches exported as JSON.

MCP server for kicktipp.com that enables AI assistants to view match data, leaderboards, and place bets through natural language.