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
The project "ppl-ai/modelcontextprotocol" is a Model Context Protocol (MCP) server connector that integrates the Perplexity Sonar API to enable real-time web search and live research capabilities for AI assistants such as Claude within the MCP ecosystem. This MCP server implementation allows Claude to perform live, web-wide research by engaging in conversations with the Sonar API, providing unparalleled access to up-to-date information from the web. The server exposes a tool called "perplexity_ask" which accepts an array of conversation messages, each containing a role and content, to facilitate interactive and dynamic web searches. The project includes detailed setup instructions, starting with cloning the repository and installing dependencies. Users need to obtain a Sonar API key by signing up for a Sonar API account and setting the API key in their environment variables. The integration is designed to work seamlessly with Claude Desktop by configuring the MCP server in Claude's configuration file, allowing Claude to utilize the Perplexity Ask MCP server for enhanced research capabilities. Additionally, the project supports Docker for containerized deployment and provides guidance on building the Docker image. It also offers troubleshooting tips and references to official documentation for further assistance. Beyond Claude, the MCP server can be integrated with other applications supporting MCP, such as Cursor, by adding the MCP server configuration to the application's settings. The project is licensed under the MIT License, allowing users to freely use, modify, and distribute the software. Overall, this MCP server connector significantly enhances AI assistants' ability to perform real-time, web-based research, making it a valuable tool for developers and users seeking to augment AI capabilities with live information retrieval.
https://github.com/ppl-ai/modelcontextprotocol
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.