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
Fast-Editor/Lynkr
Lynkr is a versatile, self-hosted proxy server designed to streamline the use of AI coding tools such as Claude Code CLI, Cursor IDE, Cline, Continue.dev, Codex CLI, and ClawdBot. It acts as an intermediary, allowing these tools to connect to a wide array of Large Language Model (LLM) providers, from cloud-based services like Databricks, AWS Bedrock, OpenRouter, Azure OpenAI, and Azure Anthropic, to local and private options like Ollama, llama.cpp, and LM Studio. The primary advantages of Lynkr include significant cost reduction (estimated 60-80%) through built-in token optimization, smart tool selection, prompt caching, and memory deduplication. It emphasizes privacy by enabling 100% local and offline operation, making it suitable for sensitive environments. The proxy is designed for flexibility, supporting both remote and local connections and offering zero-code-change integration, meaning existing AI coding tools can be configured to use Lynkr with minimal effort. It also boasts enterprise-ready features like circuit breakers, load shedding, Prometheus metrics, and health checks. Lynkr offers straightforward installation via npm, Git clone, or Docker. It supports various Node.js versions and provides comprehensive documentation for configuring each supported AI coding tool and LLM provider. This project is ideal for developers seeking provider flexibility and cost control, enterprises needing self-hosted AI with observability, and privacy-focused teams requiring local model execution.
https://github.com/Fast-Editor/Lynkr
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.