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
hyper-mcp is a fast and secure Model Context Protocol (MCP) server designed to extend its capabilities through WebAssembly plugins. It facilitates the integration of AI functionalities into applications by supporting MCP-compatible apps such as Claude Desktop and Cursor IDE. The server allows developers to write plugins in any language that compiles to WebAssembly, distribute them via standard OCI registries like Docker Hub, and run them across various environments including cloud, edge, mobile, and IoT devices. Built on the Extism framework, hyper-mcp ensures robust plugin support with sandboxing features that limit network, filesystem, and memory access, enhancing security and resource management. The server supports all three protocols defined in the MCP specification: stdio, SSE, and streamable HTTP, providing flexibility in communication methods. It is lightweight enough to operate in resource-constrained environments and offers cross-platform compatibility out of the box. Security is a core focus, with sandboxed plugins that cannot access the system without explicit permission, memory-safe execution with resource limits, secure plugin distribution through signed OCI images verified by sigstore, and fine-grained access control for host functions. Users can configure hyper-mcp through JSON configuration files specifying plugins and their runtime settings, including allowed hosts and memory limits. The server supports multiple URL schemes for plugin sources, including OCI registries, local files, HTTP/HTTPS, and Amazon S3. It integrates seamlessly with Cursor IDE, allowing project-specific or global configurations to enable tool usage through chat interfaces. The project maintains a variety of example plugins covering functionalities like time calculations, QR code generation, hashing, IP retrieval, web fetching, cryptocurrency prices, file system operations, GitHub and GitLab interactions, Python code evaluation, academic paper search, memory storage, SQLite interaction, and more. It also supports community-built plugins for news, release monitoring, finance, and cryptography. Comprehensive documentation is provided, including runtime configuration, authentication setup, security best practices, and platform-specific instructions, making hyper-mcp a versatile and secure MCP server solution for AI plugin integration.
https://github.com/hyper-mcp-rs/hyper-mcp
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.
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.
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.
World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.
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.
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...
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...
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.