openrag
OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.
OpenRAG MCP server integrates retrieval-augmented generation capabilities into AI assistants through a streamable HTTP endpoint. Built on Langflow, Docling, and OpenSearch, it enables AI clients to perform semantic search, chat with documents, ingest knowledge, and manage RAG settings. The MCP server is embedded directly in OpenRAG instances and authenticated via API key, eliminating the need for separate installations. Developers can connect tools like Cursor and Claude Desktop to query uploaded documents through natural language.
Key Features
Use Cases
- 01Connect Cursor or Claude Desktop to company documentation for code-aware assistance
- 02Enable AI assistants to answer questions from uploaded research papers and reports
- 03Build customer support agents that retrieve information from product manuals
- 04Create legal research assistants with access to case law and contract databases
- 05Integrate enterprise knowledge bases into developer workflows
- 06Power conversational interfaces over technical documentation
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
openrag — FAQ
What is the OpenRAG MCP server?+
The OpenRAG MCP server is a built-in endpoint that exposes retrieval-augmented generation capabilities to AI assistants via the Model Context Protocol. It allows clients like Cursor and Claude Desktop to chat with documents, perform semantic search, and manage knowledge bases without requiring a separate installation.
How do I connect the OpenRAG MCP server to Claude Desktop or Cursor?+
Add the OpenRAG MCP configuration to your client's settings JSON, pointing the URL to your instance's /mcp endpoint (e.g., http://localhost:3000/mcp) and include your OpenRAG API key in the X-API-Key header. The server runs automatically when OpenRAG is running.
Do I need to install a separate openrag-mcp package?+
No, the standalone openrag-mcp PyPI package is deprecated. The MCP server is now built into OpenRAG itself and accessible at the /mcp endpoint of your running instance.
Which MCP clients work with OpenRAG?+
OpenRAG's MCP server works with any client supporting streamable HTTP MCP servers, including Cursor, Claude Desktop, and IBM Bob. Authentication is handled via standard API key headers.
What API key or credentials does the MCP server require?+
You need an OpenRAG API key, which you pass in the X-API-Key header when configuring your MCP client. This is the same API key used for OpenRAG's REST API.
Is OpenRAG free to use?+
OpenRAG is open source and available on GitHub. You can self-host it freely, though you may need API keys for the underlying LLM providers you choose to use with it.
How do I install openrag?+
Open the source repository on GitHub and follow its README. openrag is a mcp server — MCP Agents Market links you directly to the official repo.
Is openrag free?+
openrag is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.