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
omni-mcp/isaac-sim-mcp
Isaac Sim MCP consists of two parts that work together: an Omniverse Kit extension loaded inside NVIDIA Isaac Sim, and a Model Context Protocol server that talks to it. The extension starts a listener on localhost port 8766 when Isaac Sim is launched with the extension folder and the isaac.sim.mcp_extension identifier enabled. The MCP server, a single Python file run with uv, connects to that listener and turns tool calls from an MCP client into simulator operations, which lets a user manipulate a running simulation conversationally instead of writing scripts. The exposed tools are get_scene_info, which pings the extension to confirm the connection and return basic scene information and which the documentation says should always be called first; create_physics_scene, which builds a scene from a list of objects with types and positions and takes a ground plane flag, a gravity vector and a scene name; create_robot, which places one of the supported robot types, franka, jetbot, carter, g1 or go1, at given coordinates; omni_kit_command, which runs an arbitrary Omni Kit command such as CreatePrim with a primitive type; and execute_script, which executes arbitrary Python inside Isaac Sim, intended for complex behaviour with proper asynchronous patterns. Documented capabilities built on these tools include dynamic robot positioning and movement, custom lighting and scene creation, obstacle navigation, USD asset search and placement, and generating 3D objects through a Beaver3D model, which along with NVIDIA services is configured with the BEAVER3D_MODEL, ARK_API_KEY and NVIDIA_API_KEY environment variables. Requirements are Isaac Sim 4.2.0 or newer, Python 3.9 or newer, uv with the mcp CLI package installed, and the Cursor editor, which is the client the setup instructions target. The MCP Inspector is suggested for development. The project is MIT licensed.
https://github.com/omni-mcp/isaac-sim-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.