Langflow Document QA

🚀 Langflow-based Document QA MCP Server

This is a Langflow-based Document QA MCP (Model Context Protocol) server. It demonstrates core MCP concepts through a simple interface and provides the function of querying documents from the Langflow backend.

🚀 Quick Start

This is a Langflow-based Document QA MCP (Model Context Protocol) server. It demonstrates the core MCP concepts through a simple interface and provides the functionality to query documents from the Langflow backend.

✨ Features

Tools

• query_docs - Query the document QA system
  • Accepts a query string as input
  • Returns the response from the Langflow backend

📦 Installation

Prerequisites

1. Create a Langflow Document QA Flow

1. Open Langflow and create a new flow from the "Document QA" template.
2. Configure your flow with the necessary components (e.g., ChatInput, file upload, LLM, etc.).
3. Save your flow.

2. Obtain the Flow API Endpoint

1. Click the "API" button in the top-right corner of Langflow.
2. Copy the API endpoint URL from the cURL command. Example: http://127.0.0.1:7860/api/v1/run/<flow-id>?stream=false
3. Save this URL as you'll need it for the API_ENDPOINT configuration.

Installation Steps

Install Dependencies

npm install

Build the Server

npm run build

Automatic Rebuilding during Development

npm run watch

Installation Guide

To use with Claude Desktop, add the following server configuration:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "langflow-doc-qa-server": {
      "command": "node",
      "args": [
        "/path/to/doc-qa-server/build/index.js"
      ],
      "env": {
        "API_ENDPOINT": "http://127.0.0.1:7860/api/v1/run/480ec7b3-29d2-4caa-b03b-e74118f35fac"
      }
    }
  }
}

Install via Smithery

Automatically install the Document QA server for Claude Desktop via Smithery:

npx -y @smithery/cli install @GongRzhe/Langflow-DOC-QA-SERVER --client claude

Environment Variables

The server supports the following environment variables for configuration:

• API_ENDPOINT: Needs to be set to the URL of your Langflow flow.
• Other relevant environment variables, such as those for authentication or logging.

💻 Usage Examples

Basic Usage

After completing the installation, run the following command to start the server:

node index.js

Ensure that the server is listening on the specified port and can handle incoming requests. You can test the server's functionality by accessing http://localhost:<port>.

🔧 Technical Details

The server is developed based on Langflow, which provides a simple interface to demonstrate the core MCP concepts. It uses the API endpoint of the Langflow flow to query documents from the backend.

📄 License

This project is licensed under [Specify the specific license information here]. Please refer to the project's LICENSE file for detailed information.