Hirag Mcp
What is Hirag Mcp
hirag_mcp is a Python server that implements the Model Context Protocol (MCP) specifically designed for the HiRAG framework, enabling efficient retrieval of information from a knowledge base.
Use cases
Use cases for hirag_mcp include academic research for retrieving relevant literature, customer support systems for querying knowledge bases, and content generation applications that require contextual information retrieval.
How to use
To use hirag_mcp, first ensure you have ‘uv’ installed to create a virtual environment. After setting up the environment and installing dependencies, you can run the server using the command ‘mcp dev server.py’. You can also index your own text files using ‘hi_indexing_openai.py’.
Key features
Key features of hirag_mcp include naive RAG retrieval and hybrid RAG retrieval, allowing for both simple and advanced search capabilities over the knowledge base.
Where to use
hirag_mcp can be used in various fields such as natural language processing, information retrieval, and any application requiring efficient access to large sets of knowledge.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Hirag Mcp
hirag_mcp is a Python server that implements the Model Context Protocol (MCP) specifically designed for the HiRAG framework, enabling efficient retrieval of information from a knowledge base.
Use cases
Use cases for hirag_mcp include academic research for retrieving relevant literature, customer support systems for querying knowledge bases, and content generation applications that require contextual information retrieval.
How to use
To use hirag_mcp, first ensure you have ‘uv’ installed to create a virtual environment. After setting up the environment and installing dependencies, you can run the server using the command ‘mcp dev server.py’. You can also index your own text files using ‘hi_indexing_openai.py’.
Key features
Key features of hirag_mcp include naive RAG retrieval and hybrid RAG retrieval, allowing for both simple and advanced search capabilities over the knowledge base.
Where to use
hirag_mcp can be used in various fields such as natural language processing, information retrieval, and any application requiring efficient access to large sets of knowledge.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
HiRAG-MCP
Python server implementing Model Context Protocol (MCP) for HiRAG.
Features
- Naive RAG retrieval
- HiRAG RAG retrieval
API
Tools
-
naive_search
- Perform a naive search over the knowledge base.
- Inputs:
query: The search query textmax_tokens(optional): Optional maximum tokens for the response
-
hi_search
- Perform a hybrid search combining both local and global knowledge over the knowledge base. (default to use)
- Inputs:
query: The search query textmax_tokens(optional): Optional maximum tokens for the response
Test
uv (recommended)
Make sure uv is installed, if not:
curl -LsSf https://astral.sh/uv/install.sh | sh
Then create the virtual environment and install dependencies using uv as below:
uv venv
source .venv/bin/activate
uv sync
Running the server
Note that we already have a test folder and test.txt file, which are the results after indexing test.txt with hi_indexing_openai.py. You can directly use the following command to run the MCP server and test the tools:
mcp dev server.py
You can also use hi_indexing_openai.py to index your own text files. Remember to adjust the working_dir in config.yaml accordingly.
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
