MCP Connector

Query Documents with Langflow

Langflow-DOC-QA-SERVER lets Claude query documents through a Langflow Document Q&A flow via one query_docs tool.

Works with langflow

91
Spark score
out of 100
Updated Apr 2025
Source checked Sep 15, 2026
Version 1.0.0
Models
claudeuniversal

Add to Favorites

Why it matters

Integrate Langflow's document question-answering capabilities into your applications. This MCP server provides a streamlined interface to query your documents and retrieve answers via the Langflow backend.

Outcomes

What it gets done

01

Connect to Langflow backend for document Q&A.

02

Execute queries against document datasets.

03

Retrieve answers from the Langflow system.

04

Debug the Q&A process using MCP Inspector.

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-langflow-doc-qa-server | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Capabilities

Tools your agent gets

query_docs

Executes a query against the document question-answering system and returns answers from the Langflow backend

Overview

Langflow-DOC-QA-SERVER MCP Server

Langflow-DOC-QA-SERVER gives Claude a single query_docs tool that forwards questions to a Langflow Document Q&A flow and returns its answer. Use it when you already have a Langflow Document Q&A flow and want to query it through Claude instead of Langflow's own UI.

What it does

Langflow-DOC-QA-SERVER is a TypeScript MCP server for document question-answering, backed by a Langflow flow rather than its own model or vector store. It gives Claude a simple interface to query documents by forwarding requests to a Langflow Document Q&A flow you build and run separately.

When to use - and when NOT to

Use it when you already have, or are willing to build, a Langflow Document Q&A flow, with components like ChatInput, File Upload, and an LLM, and want Claude to query it conversationally instead of using Langflow's own UI. It requires the Langflow flow's API endpoint URL, obtained from Langflow's API button, configured as the server's API_ENDPOINT. It has a single tool and no document-loading logic of its own; all the actual retrieval and answering happens inside your Langflow flow, so it is only as capable as the flow it's pointed at. The upstream repository (GongRzhe/Langflow-DOC-QA-SERVER on GitHub) is archived and no longer receiving updates.

Capabilities

  • query_docs: query the document Q&A system with a query string, returning the response from the connected Langflow backend

How to install

First, build a Document Q&A flow in Langflow from the built-in template, and copy its API endpoint URL, for example http://127.0.0.1:7860/api/v1/run/``?stream=false. Then add the server to Claude Desktop's config:

{
  "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"
      }
    }
  }
}

Or install automatically via Smithery:

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

If API_ENDPOINT is not set, it defaults to a placeholder Langflow flow ID, so you should always set it to your own flow's endpoint. For local development, install dependencies with npm install and build with npm run build; debug with the MCP Inspector via npm run inspector, since MCP servers communicate over stdio and are otherwise hard to inspect directly.

Who it's for

Langflow users who have already built a Document Q&A flow and want to query it through Claude conversationally, instead of using Langflow's own playground or API directly. It is released under the MIT License.

Source README

Langflow-DOC-QA-SERVER


smithery badge

Langflow Document Q&A Server MCP 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

image

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

image

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"
      }
    }
  }
}

image

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.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.