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
MFYDev/ghost-mcp
MFYDev/ghost-mcp is a TypeScript MCP server that puts the Ghost CMS Admin API behind Model Context Protocol tools, so an LLM client such as Claude can inspect and edit a Ghost site. Requests go through the official @tryghost/admin-api client with JWT authentication derived from an admin API key, and the server is configured with the GHOST_API_URL, GHOST_ADMIN_API_KEY and GHOST_API_VERSION environment variables in an MCP client configuration file; it is published to npm and normally started with npx. Ten resource types are covered: posts, members, newsletters, offers, invites, roles, tags, tiers, users and webhooks. Most follow the same browse, read, add, edit and delete pattern. Posts can be listed with filters, pagination and ordering, read by ID or slug, created with a title, content and status, updated by ID and deleted. Members can be listed, read by ID or email, created, edited and removed, and the same operations exist for newsletters, offers, tags and tiers. Users can be browsed, read by ID or slug, edited and deleted. Invites and webhooks support browsing, creation and deletion, while roles are read only. Search supports both fuzzy and exact matching, and output is formatted to be readable rather than returned as raw API payloads. Errors are wrapped in a custom GhostError type so that API communication and processing failures produce descriptive messages, and logging goes through the MCP context to help with troubleshooting. Parameter schemas for each tool live in the src/tools directory of the repository. The project is MIT licensed and aimed at people running a Ghost publication who want to manage content, membership tiers, promotional offers and newsletters from an LLM client instead of the Ghost admin interface.
https://github.com/MFYDev/ghost-mcp
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.