Langflow Document Q&A Server
A document question-and-answer server powered by Langflow.
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
- Open Langflow and create a new flow from the "Document Q&A" template
- Configure your flow with necessary components (ChatInput, File Upload, LLM, etc.)
- Save your flow
2. Get Flow API Endpoint
- Click the "API" button in the top right corner of Langflow
- Copy the API endpoint URL from the cURL command
Example:
http://127.0.0.1:7860/api/v1/run/<flow-id>?stream=false - Save this URL as it will be needed for the
API_ENDPOINTconfiguration
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 tohttp://127.0.0.1:7860/api/v1/run/480ec7b3-29d2-4caa-b03b-e74118f35facif 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.
Похожие серверы
Web Search MCP
Scrapes Google search results using a headless browser. Requires Chrome to be installed.
O'Reilly Learning Platform
Search and manage content on the O'Reilly Learning Platform.
1ly MCP
Enable AI agents to discover, launch tokens, pay for, and sell APIs and resources using x402
Google Search by CData
An MCP server for Google Search provided by CData, which requires an external CData JDBC Driver.
Source Library
Search and cite 500+ translated historical texts (alchemy, Hermeticism, Renaissance) with DOI-backed academic citations. Access rare Latin and German manuscripts from the 15th-18th centuries.
Wikipedia MCP Server
A server that enables LLMs to query and retrieve information from Wikipedia.
Deep Research
Generates in-depth research reports using powerful AI models.
MCP-NixOS
A server for searching NixOS, Home Manager, and nix-darwin resources.
Brave Search
An MCP server for web and local search using the Brave Search API.
Qdrant RAG MCP Server
A semantic search server for codebases using Qdrant, featuring intelligent GitHub issue and project management.