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
getfounded/mcp-tool-kit
MCP Tool Kit is a Python toolkit that runs a single Model Context Protocol server aggregating a large catalogue of tools instead of requiring one server per integration. Tools are discovered and registered dynamically at runtime, so adding a module does not require manual wiring. The server supports two transports: stdio for desktop clients such as Claude Desktop, and Server-Sent Events for web based access, where an HTTP endpoint exposes an /sse stream and a /messages endpoint on port 8080. The bundled catalogue covers filesystem read and write operations, time and timezone conversion, web search through Brave Search, Playwright based browser automation, data analysis sources such as Yahoo Finance, FRED and World Bank, and document manipulation for PDF, Excel and PowerPoint. Behaviour is driven by a config.yaml file where each tool group is switched on or off and given its own options, for example the list of directories the filesystem tool may touch or the maximum number of search results. API keys for the external services are supplied through an .env file copied from a template. File operations are confined to a dedicated storage directory created under the user home with documents, downloads and workspace subfolders, which the project treats as its security boundary. Installation is offered through one line install scripts for Windows PowerShell, macOS and Linux, through release archives, through a git clone with launcher scripts, or by running the published Docker image; Docker Compose commands are documented for starting, rebuilding and inspecting the server. Custom tools are written by subclassing a BaseTool class that returns a name and a map of callables, with async handlers receiving an MCP context object. The package is published on PyPI as mcptoolkit and documented on a separate site. It targets users who want a broad set of capabilities available to an assistant from one configurable server.
https://github.com/getfounded/mcp-tool-kit
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.