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
wanshuiyin/Auto-claude-code-research-in-sleep
ARIS (Auto-Research-In-Sleep) is a methodology focused on autonomous machine learning research, designed to be lightweight and work across various LLM agents such as Claude Code, Codex, and OpenClaw. It emphasizes Markdown-only skills to avoid framework lock-in and promote flexibility. The core of ARIS involves cross-model review loops, facilitating idea discovery, and automating experimental processes in ML research. The project provides flexible integration, allowing users to leverage ARIS as a skill-based workflow within existing LLM environments like Claude Code or Codex CLI, or through a standalone CLI for a complete experience. ARIS implements an 'ultracode-style deep mode' for AI agents, where a "breadth/firepower pass" adapts to the runtime (e.g., Claude Code ultracode, Codex `spawn_agent`). This pass feeds information to three key roles: breadth via cross-model review, accuracy via a research wiki, and memory also via the research wiki. A central component is the 'cross-model jury' and 'research wiki' which acts as a persistent memory and arbitration system for research loops. The methodology can be extended beyond academic research to any structured 'research' endeavor, such as investment analysis or legal research, as highlighted by 'ARIS-Anything'. The project also includes complementary tools like 'Claude Fleet' for monitoring multiple Claude Code/Codex sessions and 'ARIS-Monitor' for a minimalist real-time status display. The ARIS-Code CLI is presented as a standalone installation, showcasing continuous development with new LLM provider integrations.
https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
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.