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
langfuse/mcp-server-langfuse
Model Context Protocol server for Langfuse Prompt Management, written in TypeScript. It connects an MCP client such as Claude Desktop or Cursor to a Langfuse project so that prompts stored and versioned in Langfuse can be discovered and used directly inside the client. The server implements the MCP prompts specification: prompts/list returns the available prompt names together with their required arguments and supports cursor-based pagination, while prompts/get retrieves a single prompt and compiles it with the variables supplied by the caller. Both Langfuse text prompts and chat prompts are transformed into MCP prompt objects. Because several MCP clients do not yet implement the prompt capability, the same functionality is also exported as two ordinary tools, get-prompts and get-prompt; the first takes an optional cursor for pagination, the second takes a required prompt name and an optional JSON object of arguments. Configuration happens entirely through environment variables in the MCP client config: LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY and LANGFUSE_BASEURL, which can point at Langfuse Cloud or a self-hosted instance. Installation is a local build with npm install and npm run build, after which the compiled build/index.js is registered as a stdio command; the repository documents a Claude Desktop claude_desktop_config.json entry and a Cursor command entry, and suggests the MCP Inspector for testing. The README states known limitations: only prompts carrying the production label in Langfuse are returned, all arguments are treated as optional and carry no descriptions because Langfuse variables have no specification, and list operations require fetching each prompt individually in the background to extract its arguments, which works but is inefficient. It targets teams that already manage prompts in Langfuse and want that prompt library available to MCP-based assistants.
https://github.com/langfuse/mcp-server-langfuse
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.