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
SecretiveShell/MCP-Bridge
MCP-Bridge is middleware designed to enable seamless integration of Model Context Protocol (MCP) tools with the OpenAI API. It acts as a bridge that allows developers to use MCP tools transparently through an OpenAI-compatible interface, facilitating interoperability between MCP tools and any client that supports the OpenAI API. This middleware provides a set of REST API endpoints that expose native MCP primitives, allowing users to interact with MCP tools without needing explicit MCP support in their clients. MCP-Bridge supports both non-streaming and streaming chat completions with MCP, as well as non-streaming completions without MCP. It also supports MCP sampling and provides an SSE (Server-Sent Events) bridge for external clients, enabling chat applications with explicit MCP support to use MCP-Bridge as an MCP server. The project supports installation via Docker or manual setup, with configuration options to connect to inference engines that support tool calls, such as vLLM or ollama. Users can configure MCP servers, API key authentication for security, and network settings through a JSON configuration file. The middleware modifies incoming requests to include tool definitions for all available MCP tools, forwards these requests to the inference engine, manages tool calls, and integrates tool call results into the response returned to the OpenAI API. This design allows for flexible and secure use of MCP tools in various applications, including integration with clients like Open Web UI and compatibility with MCP clients that use STDIO through additional tools. MCP-Bridge is particularly useful for developers looking to leverage MCP tools within the OpenAI API ecosystem, providing a unified interface and simplifying the complexity of managing MCP servers. The project includes comprehensive documentation, example configurations, and support channels such as Discord for community assistance.
https://github.com/SecretiveShell/MCP-Bridge
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.