"Open source MCP (Model Context Protocol) implementations" matching MCP servers:

Searches job listings from Taiwanese job boards (104 and Yourator) and returns normalized results.

Provides live web and document intelligence, including search, company news, scraping, crawling, structured extraction, document parsing, brand intelligence, screenshots, website monitoring, and batch jobs.

An MCP server that builds structured research source packs for a topic, extracting verified facts, quotes, numbers, dates, and primary links with a coverage map of claims across sources.

Gaia Protocol—a planetary DAO for global resource management using quantum-entangled ledgers and algorithmic governance.

Local-first documentation for AI agents

Web search using free multi-engine search (NO API KEYS REQUIRED) — Supports Bing, Baidu, DuckDuckGo, Brave, Exa, and CSDN.

MCP server that gives AI agents instant access to public camera feeds worldwide via simple HTTP GET, saving snapshots to disk.

An MCP server that fetches web pages and extracts clean, AI-usable context from them, enabling tools for link discovery, content search, and integrated fetch-and-search operations.

Collection of B2B sales intelligence MCP servers. Includes website analysis, tech stack detection, hiring signals, review aggregation, ad tracking, social profiles, financial reporting and more for AI-powered prospecting

Fetches and caches public site pages from llms.txt and returns structured answers with source URLs, enabling verification of claims against live public content.

Enables AI agents to control the user's Chrome or Firefox browser, leveraging existing sessions for tasks requiring authentication and user handoff.

Enables web crawling and content extraction from web pages, supporting multiple output formats like text, markdown, XML, and JSON, with robots.txt compliance and rate limiting.

Enables AI assistants to summarize, take notes on, and answer questions about YouTube, Bilibili, and Xiaohongshu videos by providing subtitles and local speech transcription with timestamps via MCP.

A read-only MCP server that gives AI agents the web as compact, ranked, verified evidence — no API keys, no cloud retrieval, all models local.

A proxy-aware MCP server that enables web searching across multiple engines and automated markdown content extraction from webpages. It features a deep research agent for recursive searching and synthesis, supporting complex network environments through SOCKS5 and HTTP proxies.

Web search, page fetching, and research from the terminal or any MCP client — no API key required.

Transforms social media links (TikTok, Instagram, YouTube) and videos into text context with transcription, OCR, and metadata for AI agents like Claude and Cursor.

An MCP-based rule parsing engine for creating book sources, supporting CSS selectors, JSONPath, regex, and text matching to extract and validate content from HTML, JSON, or text data.

Enables Codex to control a visible Chromium browser via MCP tools for navigation, page inspection, and interaction, while keeping sensitive steps like login and captcha under the user's control.

Enables iterative deep web research through MCP clients, using SearXNG search, Crawl4AI parsing, and LLM synthesis.