Langflow-DOC-QA-SERVER

Source

A Model Context Protocol server for document Q&A powered by Langflow . It demonstrates core MCP concepts by providing a simple interface to query documents through a Langflow backend.

Catalog onlyCatalog onlySTDIO

Overview

Langflow-DOC-QA-SERVER is a Model Context Protocol (MCP) server designed for document question and answer (Q&A) systems, powered by Langflow. It provides a simple interface to query documents through a Langflow backend, demonstrating core MCP concepts.

To use the server, create a Langflow Document Q&A flow, configure it with necessary components, and obtain the API endpoint for querying. You can then send queries to the server using the provided API.

Implements a document Q&A system using MCP concepts. - Provides a query_docs tool to query documents. - Supports configuration through environment variables. - Easy integration with Claude Desktop.

Answering questions based on specific documents.
Integrating document Q&A capabilities into applications.
Assisting users in retrieving information from large document sets.

Add to your AI client

Use these steps to connect Langflow-DOC-QA-SERVER in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "langflow-doc-qa-server-gongrzhe": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langflow-doc-qa-server-gongrzhe"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "langflow-doc-qa-server-gongrzhe": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langflow-doc-qa-server-gongrzhe"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "langflow-doc-qa-server-gongrzhe": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langflow-doc-qa-server-gongrzhe"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "langflow-doc-qa-server-gongrzhe": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langflow-doc-qa-server-gongrzhe"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "langflow-doc-qa-server-gongrzhe": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langflow-doc-qa-server-gongrzhe"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "langflow-doc-qa-server-gongrzhe": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-langflow-doc-qa-server-gongrzhe"
      ]
    }
  }
}

FAQ

What is the purpose of this server?

It serves as a backend for querying documents using a structured protocol.

How do I configure the server?

You can configure it using environment variables and by setting up the API endpoint.

Is there any support for debugging?

Yes, you can use the MCP Inspector for debugging purposes.

Research and data