"A lightweight, self-hosted Git service" matching MCP servers:

Self-hosted web search and page fetch service using SearXNG metasearch and Scrapling browser rendering, exposing MCP tools for direct agent use.

An MCP server that enables AI assistants to search and retrieve Beninese government services, procedures, and requirements from service-public.bj with real-time data and smart provider routing.

Enables AI assistants to crawl and extract data from Chinese social media platforms like Bilibili, Xiaohongshu, and Douyin. Provides search, content detail retrieval, and creator information tools with persistent browser sessions and QR code login support.

A lightweight MCP server for reading public YouTube data, offering tools to fetch video transcripts, playlist contents, and video metadata without requiring an API key.

A single-process MCP server that crawls web pages, handles anti-bot challenges, converts HTML to Markdown, and caches results in PostgreSQL, providing tools to fetch and read web content.

Provides a robust interface for searching TikTok videos by hashtags and retrieving trending content, with anti-detection measures and comprehensive metadata extraction.

Enables local web crawling and scraping through MCP, providing tools to fetch pages as Markdown, extract structured data with CSS selectors, and capture full-page screenshots while managing a shared browser instance.

Provides browser automation tools for coding agents—goto, browse, goal, page_state, and summary—so agents can drive real pages through auditable, gated decisions and record traces for offline replay.

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

LinkAgent is a Python MCP server that extracts structured data from any website via Chrome DevTools Protocol. It features a plugin architecture with LinkedIn-specific extractors for feed, profiles, companies, jobs, and search, plus a Chrome extension bridge for authenticated browsing.

Enables fetching weather forecasts for Israeli cities via browser automation with Playwright, no API needed.

Gives parents and carers read-only access to their children's learning journal entries, letting them list children, browse and keyword-search observations, retrieve full notes, tags and comments, and download attached photos and videos. It works by signing in with the user's own account credentials and calling the same internal endpoints the web app uses.

Enables automated collection and AI-powered filtering of public QQ channel posts, comments, and images. Supports natural language criteria for content filtering and provides structured data storage in JSON/CSV formats.

Enables LLMs to fetch real-time, localized weather forecasts for Israeli cities by using Playwright to autonomously navigate and scrape weather2day.co.il, including handling Hebrew queries and stateful web interactions.

A round-robin API key pool for Tavily with automatic health failover and usage tracking, enabling seamless multi-key usage with MCP clients.

MCP server that lets users obtain current Israeli city weather forecasts. It uses Playwright to browse Weather2day, extract the forecast page, and feed the cleaned data back to the LLM for natural language responses.

Enables AI agents to access Hacker News data including stories, items, users, and comments via MCP tools.

An MCP server for web content extraction that converts HTML pages into clean, LLM-optimized Markdown using Mozilla's Readability. It supports batch processing, intelligent multi-page crawling, and configurable caching while respecting robots.txt standards.

Let Claude, Cursor or Cline fetch pages and run Google searches from a real Singapore mobile IP (Singtel/M1). Hosted; free 24-hour trial key.

Convert PDF, DOCX, HTML, and URLs into clean, LLM-ready markdown with tables preserved and boilerplate stripped, through three MCP tools (URL, local file, or raw bytes). Hosted API with no local dependencies; 50 free conversions with a self-serve key, then $0.002 per call.