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
MCP Google Sheets Server gives MCP clients access to Google Sheets documents. Its tools read cell ranges in A1 notation, write and append values, clear ranges, and manage the structure of a workbook — adding, renaming and deleting sheets. Batch operations let several ranges be read or updated in one call, which matters both for speed and for staying inside Google's API quotas when a model is working across a large sheet. Formatting operations cover the presentation layer rather than only values. Because a spreadsheet is a common place for small structured datasets that never justified a database, the practical use is direct: a model can read a tracking sheet, compute something and write results back, or populate a sheet from data it gathered elsewhere. Authentication uses a Google service account or OAuth credentials, and access is bounded by what that identity has been granted on specific documents — sharing a single sheet with a service account is a clean way to limit exposure. The server is TypeScript requiring Node.js 20 or newer, published on npm as mcp-gsheets, MIT licensed, with continuous integration and coverage reporting, and registered as io.github.freema/mcp-gsheets. The audience is people who keep working data in Sheets and want an assistant reading and updating it.
https://github.com/freema/mcp-gsheets
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.