microsoft/markitdown
MarkItDown is a Python tool that converts various file formats into Markdown and integrates with LLM applications via an MCP server for enhanced text analysis and document processing.
Awesome MCP › Other MCP Servers
trypeggy/facebook-ads-library-mcp
Facebook Ads Library MCP Server is a Python MCP server that gives an assistant access to the public Facebook Ads Library, so it can look up which ads a company or brand is currently running and analyze the creative. Tools include get_meta_platform_id, which resolves one or many brand names to platform IDs, and get_meta_ads, which retrieves ads for one or several pages. Creative analysis is handled by analyze_ad_image for visual elements, text, colors and composition, analyze_ad_video for a single video, and analyze_ad_videos_batch, which analyzes several videos in one call and is documented as saving roughly 88 percent of the tokens a per-video pass would use. A local media cache backs these tools, with get_cache_stats for storage statistics, search_cached_media for finding previously analyzed media by brand, colors, people or media type, and cleanup_media_cache for freeing disk space. The server batches and deduplicates calls to the upstream ads data API and monitors remaining credits to fail early rather than midway through a workflow. Self-hosting requires Python 3.12 or newer and two keys: SCRAPECREATORS_API_KEY for the ads data provider and an optional Google Gemini key used for video analysis. Install scripts for macOS, Linux and Windows create a virtual environment, install dependencies and print the client configuration to paste into Claude Desktop or Cursor; keys are read from a .env file. The maintainers also offer a hosted version at useproxy.dev that needs no keys or local setup. Typical uses are counting and classifying the ads of one brand, comparing messaging across competitors, and summarizing campaign themes across a set of companies.
https://github.com/trypeggy/facebook-ads-library-mcp
Also in Other MCP Servers
punkpeye/awesome-mcp-servers
A curated collection of Model Context Protocol (MCP) servers that enable AI models to securely interact with local and remote resources through standardized server implementations.
modelcontextprotocol/servers
The Model Context Protocol Servers repository offers reference implementations and third-party integrations that demonstrate how MCP enables Large Language Models to securely access and interact with diverse tools and data sources.
koala73/worldmonitor
World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.
headroomlabs-ai/headroom
Headroom is a context compression layer for AI agents, reducing token usage by 60-95% while preserving accuracy, implemented as a library, proxy, and MCP server.
diegosouzapw/OmniRoute
OmniRoute is a free AI gateway that connects various AI tools and models from over 230 providers through a single endpoint, featuring token compression, smart auto-fallback, and support for Model C...
rohitg00/ai-engineering-from-scratch
This comprehensive curriculum teaches AI engineering from scratch, focusing on building AI algorithms, agents, and MCP servers hands-on, covering everything from mathematical foundations to autonom...
every-app/open-seo
Open source, self-hostable SEO platform that exposes its keyword, rank, backlink and site-audit data to AI agents through an MCP server and a set of companion agent skills.