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
nguyenvanduocit/all-in-one-model-context-protocol
MyMCP Server is a Go implementation of a Model Context Protocol server that bundles integrations for several developer and productivity services into a single process. Its tool groups cover Confluence pages, including search through CQL and creating and updating pages; Jira issues; GitLab; Google Calendar, with tools to create, list, update and respond to events; YouTube; fetching and scraping web content; scripting; retrieval-augmented generation backed by Qdrant; and AI-assisted search and reasoning through Gemini and Deepseek. A hidden ENABLE_TOOLS environment variable takes a comma-separated list of tool groups, so an operator can expose only the integrations a given client needs; leaving it empty enables all of them. Configuration is otherwise a single .env file holding the credentials for whichever services are turned on, such as Atlassian host, e-mail and token, GitLab host and token, Brave, OpenAI, Deepseek and Google AI keys, Qdrant host, port and key, Google token and service-account credential files, and an optional proxy URL. Google service-account credentials are needed for the more involved features such as Google Chat, while the plain token file covers the other Google services. It requires Go 1.23.2 or later, installs with go install, and is registered in a Claude Desktop configuration as a command taking the path to the env file; a Smithery package offers an interactive install for Claude Desktop instead. The important caveat is stated at the top of the README: the project has been discontinued in this form and split into individual repositories, namely Google Kit for Gmail, Calendar and Chat, RAG Kit for retrieval and memory, Dev Kit for Jira, Confluence, GitLab and GitHub, Fetch Kit for fetching and scraping, and Research Kit for research and reasoning tools. It is listed as a broad multi-service MCP server rather than one belonging to a single domain.
https://github.com/nguyenvanduocit/all-in-one-model-context-protocol
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.