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
DeepSeek MCP Server is a Model Context Protocol (MCP) server designed to integrate DeepSeek's advanced language models seamlessly with MCP-compatible applications such as Claude Desktop. It acts as a proxy to the DeepSeek API, allowing anonymous usage while providing a robust interface for multi-turn conversations and extensive configuration options. The server supports automatic model fallback, switching between DeepSeek's R1 model (deepseek-reasoner) optimized for technical and complex queries, and the v3 model (deepseek-chat) recommended for general-purpose use. Users can query available models, configuration options, and current settings through natural language commands, making it highly interactive and user-friendly. The server maintains complete message history and context across exchanges, preserving configuration settings throughout conversations. This multi-turn conversation support is crucial for training and fine-tuning dialogue models, as well as managing complex interactions such as multi-step reasoning, interactive troubleshooting, and detailed technical discussions. The server handles all context management and message formatting internally, allowing users to focus on the interaction without worrying about conversation state management. Installation can be done manually via npm or automatically through Smithery for Claude Desktop integration. The server is compatible with MCP Inspector for local testing, enabling developers to view available tools, test chat completions, debug responses, and monitor performance. Configuration options include custom model selection, temperature control, max tokens limit, top P sampling, presence penalty, and frequency penalty, providing fine-grained control over model behavior. Overall, DeepSeek MCP Server offers a powerful, flexible, and user-friendly solution for leveraging DeepSeek's language models within the MCP ecosystem, supporting advanced conversational AI applications with ease and reliability.
https://github.com/DMontgomery40/deepseek-mcp-server
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.