ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
RAGFlow MCP server provides integration with RAGFlow, an open-source Retrieval-Augmented Generation engine that combines advanced RAG capabilities with agent functionality. This server enables AI assistants to access RAGFlow's document parsing, knowledge extraction, and context management features through the Model Context Protocol. It allows developers to leverage RAGFlow's deep document understanding and agentic workflows directly within MCP-compatible applications, making it easier to build production-ready AI systems with reduced hallucinations and grounded citations.
Key Features
Use Cases
- 01Building question-answering systems with verifiable citations from enterprise document repositories
- 02Creating AI agents that process and extract insights from heterogeneous data sources
- 03Developing chatbots with reduced hallucinations through grounded document retrieval
- 04Automating knowledge extraction from scanned documents and complex file formats
- 05Setting up multi-modal document understanding workflows that analyze images within PDFs
- 06Orchestrating agentic workflows with memory and context management for complex tasks
Related MCP Servers
View morepublic-apis
A collective list of free APIs
awesome-python
The definitive list that answers "I want to do X in Python, which tool should I use?"
awesome-selfhosted
A list of Free Software network services and web applications which can be hosted on your own servers
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
ragflow — FAQ
What is the RAGFlow MCP server?+
The RAGFlow MCP server is an integration that connects RAGFlow's open-source Retrieval-Augmented Generation engine to AI applications through the Model Context Protocol. It enables access to RAGFlow's document parsing, knowledge extraction, and agent capabilities from MCP-compatible clients.
How do I install the RAGFlow MCP server?+
RAGFlow requires Docker 24.0.0+ and Docker Compose v2.26.1+ with at least 4 CPU cores, 16GB RAM, and 50GB disk space. Clone the repository from GitHub, configure vm.max_map_count to at least 262144, then run docker compose up to start the server. The service will be accessible via HTTP on your machine's IP address.
Do I need API keys to use RAGFlow?+
Yes, you need to configure API keys for the LLM services you plan to use. Update the service_conf.yaml.template file with your chosen LLM factory and corresponding API key for models like GPT-5, DeepSeek, or Gemini.
Is RAGFlow free to use?+
Yes, RAGFlow is open-source software released under the Apache 2.0 license and free to use. A cloud-hosted version is also available at cloud.ragflow.io, though pricing for the cloud service may vary.
Which AI clients work with the RAGFlow MCP server?+
RAGFlow supports MCP integration and provides a skill on OpenClaw for accessing datasets. It can work with any MCP-compatible client, though specific client compatibility depends on your deployment configuration.
What document formats does RAGFlow support?+
RAGFlow supports Word documents, PowerPoint slides, Excel spreadsheets, TXT files, images, scanned copies, structured data, web pages, and PDFs with multi-modal image analysis. It uses deep document understanding to extract content from complex formats.
How do I install ragflow?+
Open the source repository on GitHub and follow its README. ragflow is a mcp server — MCP Agents Market links you directly to the official repo.
Is ragflow free?+
ragflow is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.