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
koala73/worldmonitor
World Monitor is a comprehensive, open-source global intelligence dashboard designed to provide real-time situational awareness. It integrates over 500 curated news feeds across 15 categories, using AI to synthesize briefs. The platform features a dual map engine, including a 3D globe (globe.gl) and a WebGL flat map (deck.gl), with 56 distinct map layer types for detailed visualization. A key capability is cross-stream correlation, identifying convergence signals across military, economic, disaster, and escalation events. It also includes a server-authoritative Country Instability Index (CII v8) that scores stress for 31 Tier-1 countries. For financial monitoring, it offers a finance radar tracking 29 stock exchanges, commodities, crypto, and a 7-signal market composite. The system supports local AI operations using Ollama, eliminating the need for external API keys. It offers six distinct site variants (world, tech, finance, commodity, happy, energy) built from a single codebase and provides native desktop applications for macOS, Windows, and Linux via Tauri 2. Furthermore, it supports 25 languages with native-language feeds and right-to-left (RTL) support. The project exemplifies how the Model Context Protocol (MCP) can facilitate the integration and presentation of complex, real-time data from diverse sources into a cohesive intelligence platform, leveraging its server-side capabilities for data processing and client-side integrations for rich user interfaces.
https://github.com/koala73/worldmonitor
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.
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.
wanshuiyin/Auto-claude-code-research-in-sleep
ARIS (Auto-Research-In-Sleep) is a lightweight, framework-agnostic methodology and set of skills for autonomous ML research, enabling cross-model review loops, idea discovery, and experiment automa...