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
integromat/make-mcp-server
Make MCP Server is a Node.js implementation of the Model Context Protocol that turns automation scenarios built in Make (formerly Integromat) into tools an AI assistant can call. The README marks this package as the legacy option and points to a newer cloud-based Make MCP server as the recommended choice for most use cases. On start the server authenticates against a Make account with an API key and enumerates every scenario configured with On-Demand scheduling. For each of those scenarios it parses and resolves the input parameters, so the connected model receives meaningful parameter names and descriptions instead of opaque identifiers. The assistant can then invoke a scenario with arguments, and the server returns the scenario output as structured JSON so the model can interpret the result rather than parse free text. The stated purpose is to keep complex automation logic where it already lives, inside Make, while exposing that logic as a tool surface for AI systems and creating two-way communication between an assistant and existing workflows. Setup targets Claude Desktop and any other MCP client: the server is published on npm as @makehq/mcp-server and is launched through npx from the mcpServers section of the client configuration file. Three environment variables are required, namely MAKE_API_KEY generated in a Make profile with the scenarios:read and scenarios:run scopes, MAKE_ZONE for the zone where the organization is hosted such as eu2.make.com, and MAKE_TEAM for the team identifier taken from the URL of the team page. Prerequisites are NodeJS and an MCP client. The project is written in TypeScript and maintained under the Integromat GitHub organization. It suits teams that already run Make automations and want an assistant to trigger them, with the caveat that maintainers now recommend the hosted successor.
https://github.com/integromat/make-mcp-server
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.