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
dicom-mcp lets an assistant query, read and move data on DICOM servers such as a PACS or VNA — the archives where hospitals store medical images and reports. Its tools follow the DICOM information hierarchy, which is what makes a clinical question answerable in steps: query_patients finds a patient, query_studies lists that patient's imaging studies, query_series lists the series within a study, and further tools retrieve or move the data. A notable addition is extracting text from PDF documents stored as DICOM objects, which is how radiology reports are commonly archived — so the assistant can read the actual report narrative rather than only the image metadata. The README gives a representative exchange: asked whether there were significant findings in a patient's previous CT report, the model chains the query tools and then extracts the report text, answering with the finding it contains. It is a Python project requiring 3.12 or newer, published on PyPI as dicom-mcp and MIT licensed. Two things follow from the domain rather than the code: this touches patient data, so deployment sits inside whatever regulatory regime applies, and it is a research and tooling project, not a certified medical device. The audience is medical imaging researchers and clinical informatics teams.
https://github.com/ChristianHinge/dicom-mcp
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.
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.
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.
World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.
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.
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...
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...
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.