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
translated/lara-mcp
lara-mcp is the official Model Context Protocol server for Lara Translate, the translation service from Translated. It gives an MCP client access to Lara Translation Language Models, which are trained on professionally translated segments and aim at domain-specific output rather than the generic phrasing of a general purpose model. The tool set covers four areas. Translation is a single translate tool that moves text between languages and accepts context, instructions, a translation memory, a glossary and a style setting of faithful, fluid or creative. Language detection provides detect_language for one text or an array of texts and list_languages for the supported language codes. Translation memory management provides list_memories, create_memory, update_memory and delete_memory, plus add_translation and delete_translation for individual source and target pairs, import_tmx for loading a TMX file and check_import_status for following the resulting job. Glossary management mirrors that with list_glossaries, get_glossary, create_glossary, update_glossary, delete_glossary, add_glossary_entry, delete_glossary_entry, import_glossary_csv, check_glossary_import_status, export_glossary and get_glossary_counts. The default deployment is the hosted endpoint at mcp-v2.laratranslate.com, which the client reaches by URL alone: authentication is OAuth 2.0, so the client opens a browser, the user signs in with Lara credentials and no API key is stored in the configuration. The README gives step by step setup for Claude Desktop connectors, Cursor and Claude Code plugin marketplaces, and points to a separate client setup guide for VS Code with GitHub Copilot, Windsurf, Cline and Continue. As an alternative, access key authentication passes a Lara access key id and secret in the client configuration, and the server can be self-hosted over stdio through npx from the published npm package or from the Docker image.
https://github.com/translated/lara-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.