MCP テストサーバー

by watamoo

AI/Data & Knowledge OpenAI Vector Database RAG Python

This is a Python server using the Model Context Protocol (MCP) to provide a RAG (Retrieval Augmented Generation) system leveraging OpenAI's vector store capabilities. It allows you to create and query vector databases from local files.

View on GitHub

Last updated: N/A

What is MCP テストサーバー?

The MCP テストサーバー is a Python server that utilizes the Model Context Protocol (MCP) to create and query vector databases using OpenAI's vector store functionality. It enables Retrieval Augmented Generation (RAG) by retrieving relevant information from local files and using it to enhance generation tasks.

How to use MCP テストサーバー?

Initialize the project and create a virtual environment using uv init mcp-test-server and uv venv .venv. 2. Activate the virtual environment. 3. Install the required packages using uv sync. 4. Set the OpenAI API key in a .env file. 5. (Optional) Test the server using MCP Inspector. 6. Integrate with Claude app by adding configuration to the Claude desktop app's config file.

Key features of MCP テストサーバー

Creates vector databases from files (text, PDF, DOCX, Markdown)
Queries vector databases to retrieve relevant information
Uses OpenAI's vector store capabilities
Integrates with Claude app

Use cases of MCP テストサーバー

Building a knowledge base from local documents
Enhancing chatbot responses with relevant information
Improving the accuracy of question answering systems
Creating a RAG system for specific domains

FAQ from MCP テストサーバー

What is MCP?

Model Context Protocol

What is RAG?

Retrieval Augmented Generation

What file types are supported for vector DB creation?

Text, PDF, DOCX, and Markdown files are supported.

How do I set the OpenAI API key?

Create a .env file and set the OPENAI_API_KEY variable.

How do I integrate this with Claude?

Add the provided configuration to Claude's configuration file, replacing the path with your project's absolute path.