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
mackenly/mcp-fathom-analytics
MCP Fathom Analytics is an unofficial Model Context Protocol server that gives an AI assistant read access to Fathom Analytics, a privacy-focused website analytics service. It is written in TypeScript, published to npm as mcp-fathom-analytics and run with npx, and it is also listed on Smithery for automatic installation into Claude Desktop. Internally it calls the Fathom REST API through the unofficial @mackenly/fathom-api SDK; the author states the project is not affiliated with, endorsed by or supported by Fathom Analytics. Five tools are exposed. get-account returns details about the connected Fathom account. list-sites enumerates the sites tracked under it. list-events lists the events recorded for a chosen site. get-current-visitors reports real-time data about visitors currently on a site. get-aggregation is the substantial one: it wraps the Fathom aggregation endpoint and accepts an entity and entity identifier, a list of aggregates such as pageviews, uniques, visits or average duration, a date grouping, a field grouping, and sorting and limit parameters. The README works through example payloads that show the shape of those calls, including daily pageview statistics over a month, per-page performance grouped by pathname and sorted by pageviews, and traffic broken down by country code. The five underlying REST endpoints are documented as well, covering account, sites, events, aggregations and current visitors. Configuration is a single mcpServers entry that runs the npx command with the FATHOM_API_KEY environment variable set, and the README points to the Model Context Protocol client list for other hosts. Because every tool is read-only, the server suits site owners who want to ask questions about their traffic in natural language instead of assembling dashboards, and anyone who wants an assistant to pull analytics figures into a written report. The project is MIT licensed.
https://github.com/mackenly/mcp-fathom-analytics
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.