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
adityak74/mcp-scholarly
mcp-scholarly is a small Model Context Protocol server whose purpose is finding accurate academic articles for an assistant. It currently implements one tool, search-arxiv, which takes a required keyword string and returns articles from the arXiv repository that match it. The author states that more scholarly vendors are planned, so the arXiv backend is intended as the first of several academic sources behind the same interface. The server is written in Python and packaged for uv, which shapes how it is installed and run. For Claude Desktop the README documents three configurations that are added to the mcpServers section of claude_desktop_config.json on macOS or Windows: an unpublished development entry that runs uv with the --directory flag pointed at a local checkout, a published entry that simply runs uvx mcp-scholarly, and a container entry that runs the mcp/scholarly Docker image with docker run --rm -i. Installation can also be automated for Claude Desktop through Smithery using its CLI, which writes the client configuration for the user. The development workflow is documented as well: uv sync to reconcile dependencies and update the lockfile, uv build to produce source and wheel distributions in dist, and uv publish to push them to PyPI with credentials supplied either as a token or as a username and password, through flags or UV_PUBLISH environment variables. Because MCP servers communicate over stdio, the README recommends the MCP Inspector for debugging and gives the npx command that launches the inspector against a local checkout, after which a browser URL is printed. The repository carries a Smithery badge, an MseeP security assessment badge and a Glama server badge, and includes screenshots demonstrating searches. It suits researchers and anyone who wants a chat assistant to pull real paper listings rather than recalled citations.
https://github.com/adityak74/mcp-scholarly
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.