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
andybrandt/mcp-simple-pubmed
MCP Simple PubMed is a Python Model Context Protocol server that gives an AI assistant access to the PubMed biomedical literature database through the NCBI Entrez API. It exposes a search tool that accepts the full PubMed query syntax, including keywords, MeSH terms, author names, date ranges and Boolean operators, a tool that downloads full text where it is available for open access articles in PubMed Central, and resource URIs that return article abstracts and metadata. Full text is returned as XML rather than flattened plain text, on the argument that the markup gives a model extra information about document structure. Since version 0.1.14 the server also ships MCP prompts that help construct effective queries: a systematic review prompt that generates a comprehensive strategy with MeSH terms, synonyms and date filters, a PICO prompt that builds a clinical question search from population, intervention, comparison and outcome, and an author prompt that finds all publications by one author with correct name formatting. Installation is either pip install mcp-simple-pubmed or an automated Smithery install for Claude Desktop, and the server is registered in claude_desktop_config.json as python -m mcp_simple_pubmed. Two environment variables control it: PUBMED_EMAIL, which NCBI requires, and an optional PUBMED_API_KEY that raises the rate limit from three to ten requests per second. No client-side rate limiting is implemented, on the assumption that normal assistant usage stays below the limit. The README notes that a missing full text does not always mean the article is unavailable, since publisher sites may block automated fetches while a normal browser succeeds, and that paywalled papers remain out of reach. It also documents a macOS fix for SSL certificate verification failures. The project is MIT licensed and aimed at researchers and clinicians doing literature review with an assistant.
https://github.com/andybrandt/mcp-simple-pubmed
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.