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
every-app/open-seo
OpenSEO is an open source alternative to hosted SEO suites such as Semrush and Ahrefs, built around a pay-as-you-go model in which the operator supplies a DataForSEO API key and pays only for the data actually requested. The web application covers the common SEO workflows directly: keyword research, rank tracking, competitor insights, backlink analysis, site audits and AI visibility reporting. Rather than bundling those into a single large suite, the interface keeps each workflow separate and narrow. The part that makes the project relevant to the Model Context Protocol is its agent interface. OpenSEO ships an MCP server that lets clients such as Claude Code and other MCP-capable agents query the same SEO data the web interface uses, so an agent can run keyword research or read audit results as tool calls instead of scraping a dashboard. On top of the MCP server the project publishes reusable agent skills — packaged workflows that walk an agent through a multi-step SEO task using those tools — and documents how to install both. The codebase is TypeScript. Deployment supports three paths: a hosted subscription run by the maintainers, a Docker setup intended for local single-user testing, and a Cloudflare deployment that the project recommends for internet-facing or team use and that works on Cloudflare's free plan. All self-hosted paths require the user's own DataForSEO credentials, since that service supplies the underlying search data. The project is aimed at developers, agencies and site owners who want SEO tooling they can fork and modify, and at anyone wiring SEO data into an agent workflow through MCP rather than through a proprietary dashboard.
https://github.com/every-app/open-seo
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...
wanshuiyin/Auto-claude-code-research-in-sleep
ARIS (Auto-Research-In-Sleep) is a lightweight, framework-agnostic methodology and set of skills for autonomous ML research, enabling cross-model review loops, idea discovery, and experiment automa...