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
zoedsoupe/anubis-mcp
Anubis MCP is a Model Context Protocol SDK for Elixir, published on Hex as anubis_mcp, offering complete client and server implementations built on the concurrency and fault tolerance of the BEAM. On the server side, tools, prompts and resources are defined as components: a module uses Anubis.Server.Component with a declared type, describes its arguments through a schema block with field definitions including types, required flags, length limits and descriptions, and implements an execute callback that returns a response together with the request frame. Components can be registered statically at compile time with a component declaration inside a module that uses Anubis.Server, or dynamically at runtime through register_tool on the frame. The server is started as a child of the application supervisor with a transport option, and HTTP deployments forward a router path to Anubis.Server.Transport.StreamableHTTP.Plug, which works from a plain Plug router or a Phoenix router. The client side is also a supervised child, configured with a name, a transport such as streamable_http with a base URL, client info and a protocol version, after which Anubis.Client.call_tool invokes tools on a remote server. Version 1.x supports MCP specification versions 2024-11-05, 2025-03-26, 2025-06-18 and 2025-11-25; version 2.0 drops 2024-11-05 and removes the deprecated HTTP plus SSE transports on both client and server in favour of streamable HTTP. The project documents a deprecation policy mirroring the upstream specification, where deprecated features survive at least one minor cycle with a migration path and removals happen only in major releases. Three worked examples are included in the repository: a Plug based upcase server, a Phoenix based echo server and a Phoenix LiveView ascii server with a UI. The library is LGPL-v3 licensed with documentation on HexDocs.
https://github.com/zoedsoupe/anubis-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.