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
DeepLcom/deepl-mcp-server
deepl-mcp-server is the vendor-maintained MCP server for DeepL, the machine-translation service. Its tools cover four areas. Text translation handles strings between the supported language pairs, including the regional variants DeepL distinguishes. Document translation submits a whole file and returns the translated document, preserving formatting, which is a different DeepL endpoint from text translation and involves an upload and polling cycle the server handles. Rephrasing rewrites text in the same language, DeepL Write's function, useful for tightening or adjusting the register of a passage rather than changing its language. Glossary and style rule lookups let a model consult the account's configured terminology and style settings, so translations respect the terms an organisation has standardised instead of the model's defaults. The server is JavaScript, requires Node.js 18 or newer, communicates over stdio and is normally launched by the client; it exits immediately if DEEPL_API_KEY is unset, which makes misconfiguration obvious rather than silent. It is published on npm as deepl-mcp-server and is MIT licensed. Being official, its tool coverage tracks the DeepL API and its behaviour matches the documented service. The audience is teams doing localisation work who want translation available inside an assistant session with their own glossaries applied.
https://github.com/DeepLcom/deepl-mcp-server
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.