Langflow Document QA Server

What is Langflow Document QA Server about?

Langflow Document QA Server enables document question‑answering by forwarding user queries to a Langflow flow that processes uploaded files with a language model. It implements the Model Context Protocol (MCP) so client applications can invoke the query_docs tool via stdio.

How to use Langflow Document QA Server?

1. Create a Langflow Document Q&A flow – use the built‑in template, add components such as ChatInput, File Upload, and an LLM, then save the flow.
2. Obtain the Flow API endpoint – click the API button in Langflow and copy the endpoint URL (e.g., http://127.0.0.1:7860/api/v1/run/<flow-id>?stream=false).
3. Configure the server – set the API_ENDPOINT environment variable to the copied URL.
4. Run the server – install and start the MCP server (see Server Configuration section).
5. Invoke the tool – from any MCP‑compatible client, call the query_docs tool with a query string; the server returns Langflow’s response.

Key Features

• query_docs tool – accepts a natural‑language query and returns answers generated by the Langflow backend.
• TypeScript implementation – robust type safety and easy integration into Node.js environments.
• Auto‑rebuild watch mode – npm run watch recompiles on source changes for rapid development.
• Debugging with MCP Inspector – npm run inspector launches a web UI to monitor stdio communication.
• Claude Desktop integration – pre‑made configuration snippet for seamless use within Claude Desktop.

Use Cases

• Internal knowledge bases – answer employee questions from uploaded policy documents or manuals.
• Customer support – embed a Q&A assistant that pulls information from product PDFs and help guides.
• Research assistance – query academic papers or reports without leaving the chat interface.
• Rapid prototyping – developers can test Langflow flows locally before deploying to production.

FAQ

Q: Do I need a Langflow account? A: No, Langflow can be run locally; just install it and create the required flow.

Q: Which environment variables are required? A: Only API_ENDPOINT is needed; it defaults to a sample endpoint if omitted.

Q: How do I debug communication issues? A: Run npm run inspector to launch the MCP Inspector, which shows request/response logs.

Q: Can I run the server on a remote machine? A: Yes, as long as the Langflow API endpoint is reachable from the server's network.

Q: What Node.js version is supported? A: The project targets the current LTS version of Node.js (≥18).

Server Configuration

{
  "mcpServers": {
    "langflow-doc-qa-server": {
      "command": "npx",
      "args": ["-y", "@GongRzhe/Langflow-DOC-QA-SERVER"],
      "env": {
        "API_ENDPOINT": "http://127.0.0.1:7860/api/v1/run/480ec7b3-29d2-4caa-b03b-e74118f35fac"
      }
    }
  }
}

Langflow-DOC-QA-SERVER

A Model Context Protocol server for document Q&A powered by Langflow

This is a TypeScript-based MCP server that implements a document Q&A system. It demonstrates core MCP concepts by providing a simple interface to query documents through a Langflow backend.

Prerequisites

1. Create Langflow Document Q&A Flow

1. Open Langflow and create a new flow from the "Document Q&A" template
2. Configure your flow with necessary components (ChatInput, File Upload, LLM, etc.)
3. Save your flow

2. Get 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 it will be needed for the API_ENDPOINT configuration

Features

Tools

• query_docs - Query the document Q&A system
  • Takes a query string as input
  • Returns responses from the Langflow backend

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

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"
      }
    }
  }
}

Installing via Smithery

To install Document Q&A Server for Claude Desktop automatically 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: The endpoint URL for the Langflow API service. Defaults to http://127.0.0.1:7860/api/v1/run/480ec7b3-29d2-4caa-b03b-e74118f35fac if not specified.

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

📜 License

This project is licensed under the MIT License.