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
Think MCP implements the think tool described in an Anthropic engineering article on letting a model stop and reason during complicated tool use. The tool does exactly one thing: it accepts a thought and appends it to the log. It reads nothing, writes to no database and changes no environment. What it provides is a place for the model to write down its reasoning as a step in the conversation, which turns implicit reasoning into an explicit turn the model can then read back — helping it process the output of a previous tool call, notice that it needs to backtrack, or check its intended action against a detailed policy before taking it. The referenced article reports improved evaluation metrics from adding this tool, including for models without strong native reasoning, and the repository includes the tau-bench chart from that work. The cases where it helps most are analysing tool output, and policy-heavy environments where a sequence of constraints must be verified before acting. It is a small Python project. The value proposition is unusual among MCP servers: no integration, no credentials and no external dependency, just a structural affordance for the model. The audience is anyone building agents that chain many tool calls, where wrong intermediate conclusions compound.
https://github.com/Rai220/think-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.