Langflow Doc QA Server

What is Langflow Doc QA Server about?

Langflow Doc QA Server is a TypeScript‑based MCP server that forwards natural‑language queries to a Langflow Document Q&A flow and returns the generated answers. It acts as a bridge between Claude (or any MCP‑compatible client) and a Langflow workflow that handles document retrieval, language model inference, and response formatting.

How to use Langflow Doc QA Server?

1. Create a Document Q&A flow in Langflow – start from the built‑in template, add components such as ChatInput, File Upload, and an LLM, then save the flow.
2. Obtain the flow’s API endpoint – click the API button in Langflow and copy the 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. Build and run:

   npm install
   npm run build   # produces build/index.js
   node build/index.js
   

   For Claude Desktop, add the following entry to claude_desktop_config.json (adjust the path and endpoint as needed):

   {
     "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/<flow-id>?stream=false" }
       }
     }
   }
   

Key features of Langflow Doc QA Server

• query_docs tool: Accepts a plain text query and returns the answer generated by the Langflow backend.
• Environment‑driven configuration: Only the API_ENDPOINT variable is required; defaults to a sample local endpoint.
• Standard MCP communication: Works over stdio, making it compatible with any MCP client (Claude Desktop, custom scripts, etc.).
• Developer‑friendly workflow: TypeScript source, npm scripts for build, watch, and debugging via the MCP Inspector.

Use cases of Langflow Doc QA Server

• Internal knowledge bases – let employees ask questions about uploaded PDFs, manuals, or wiki pages.
• Customer support – feed product documentation into Langflow and provide instant answers through a chat interface.
• Research assistance – query academic papers or reports without leaving the chat environment.
• Rapid prototyping – experiment with different LLMs or retrieval strategies by swapping components inside the Langflow flow.

FAQ from the Langflow Doc QA Server

Q: Do I need a Langflow license? A: No, the server works with any locally running Langflow instance; a free community edition is sufficient.

Q: Which LLM models are supported? A: Whatever model you configure inside the Langflow flow (OpenAI, Anthropic, locally hosted models, etc.).

Q: Can I run the server in production? A: Yes, but ensure the Langflow service is secured and the API_ENDPOINT points to a protected URL. Use HTTPS and authentication if needed.

Q: How do I debug request failures? A: Run npm run inspector to launch the MCP Inspector, which provides a web UI showing stdin/stdout exchange and error details.

Q: Is there a Docker image? A: Not provided in the repository, but you can containerize it by installing dependencies and running the built entry point.

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.