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
teslamate-mcp is a Model Context Protocol server that hands a TeslaMate database to an AI client. TeslaMate records everything a Tesla does into PostgreSQL, and its Grafana dashboards answer the questions someone thought of in advance; this server covers the ones that come later, such as whether the battery is really degrading or was simply cold, what home charging cost compared with public charging, or which drive was unusually inefficient. It publishes 35 tools: 30 analytics and search queries, a run_sql escape hatch for anything the fixed queries do not cover, live schema introspection, and 3 interactive chart tools. Every report takes optional arguments for car_name, days, limit and various thresholds, and calling one with no arguments returns the full classic report. The chart tools show_charging_curve, show_battery_degradation and show_drive_route render self-contained SVG on clients that support MCP Apps and return the same rows everywhere else. Safety is handled by defaulting to reads: run_sql executes inside a READ ONLY transaction that is always rolled back, and the single write tool is disabled by default and can only touch one column. Both transports are supported, stdio for Claude Desktop and Cursor and streamable HTTP with bearer authentication for everything else, served at /mcp with a /health probe. It needs a running TeslaMate with PostgreSQL and Python 3.11 or newer, or just Docker, with multi-architecture amd64 and arm64 images published to GHCR on every release. New queries are added without writing Python by dropping a .sql file and a .toml sidecar into the queries directory, where a registry picks them up. The README warns that the database is a location history and should stay on a private network behind a VPN or Tailscale. Licensed under MIT, with documentation kept in the project wiki.
https://github.com/cobanov/teslamate-mcp
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.
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.
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.
World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.
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.
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...
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...
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.