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
HubSpot MCP Server connects an MCP client to a HubSpot account so a model can read and write CRM records directly. The tools concentrate on the operations that dominate day-to-day CRM use: retrieving and creating contacts and companies, and reading engagement data such as recent activity on a pipeline. Two implementation choices address HubSpot API constraints. A local cache reduces repeated calls for data that has not changed, which both speeds up responses and keeps usage inside rate limits. A FAISS vector store indexes previously retrieved records and interactions, so semantic search over past context is answered locally instead of by paging through the API — useful when a multi-step workflow needs to recall something fetched earlier in the same session. The server is written in Python and distributed as a Docker image on Docker Hub, with the HubSpot access token supplied as configuration; the README emphasises that setup is a single container run. Documented example prompts show the intended shape of use: pasting a LinkedIn profile and asking for matching contact and company records to be created, or asking for a summary of recent pipeline movement. It is MIT licensed. The audience is sales and revenue teams whose data lives in HubSpot and who want an assistant able to query and update it conversationally.
https://github.com/peakmojo/mcp-hubspot
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.