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
taskade/mcp
Taskade MCP is the official Model Context Protocol integration for Taskade, a collaborative workspace for projects, tasks and AI agents. The repository holds two packages. The first, published on npm as @taskade/mcp-server and called the Workspace MCP, is a TypeScript server that lets any MCP client read and write workspace content. The second, an OpenAPI codegen package, generates MCP tools from any OpenAPI specification and is not limited to Taskade. The server ships 62 tools grouped by resource: workspace tools list workspaces and folders and create projects; project tools get, create, copy, complete and restore projects, list members, custom fields, blocks and tasks, and manage the public share link; task tools get, create, update, delete, complete and reopen tasks, move them within a project, manage assignees, due dates, notes and custom field values. Further groups cover AI agents, agent chat, webhooks, knowledge bases, templates, media and sharing. Authentication uses a personal access token created on the Taskade API settings page and passed as the TASKADE_API_KEY environment variable. The README gives copy-paste configuration for Claude Desktop, Cursor, Windsurf, Cline and VS Code, all launching the package through npx, plus an HTTP and SSE mode started with a --http flag that listens on port 3000 and accepts an access token as a query parameter. The documentation is explicit that Taskade speaks MCP through three separate surfaces and helps the reader choose: this local Workspace MCP server for workspace content, a hosted OAuth-protected Genesis App MCP at taskade.com/mcp for editing a published app from an IDE, and in-product MCP Connectors for letting Taskade agents reach services such as Slack, Shopify and Gmail. Some endpoints are noted as gated on free plans.
https://github.com/taskade/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.