{"type":"mcp_server","name":"Langflow-DOC-QA-SERVER","description":"This repository provides a Model Context Protocol (MCP) server for document question answering, leveraging Langflow to create a backend for querying documents. It offers a simple interface to interact with","category":"AI","language":"JavaScript","stars":15,"forks":0,"owner":"GongRzhe","github_url":"https://github.com/GongRzhe/Langflow-DOC-QA-SERVER","homepage":null,"setup":"## Setup\n\n### 1. Create Langflow Document Q&A Flow\n1. Open Langflow and create a new flow from the \"Document Q&A\" template\n2. Configure your flow with necessary components (ChatInput, File Upload, LLM, etc.)\n3. Save your flow\n\n### 2. Get Flow API Endpoint\n1. Click the \"API\" button in the top right corner of Langflow\n2. Copy the API endpoint URL from the cURL command\n   Example: `http://127.0.0.1:7860/api/v1/run/<flow-id>?stream=false`\n3. Save this URL as it will be needed for the `API_ENDPOINT` configuration\n\nTo use with Claude Desktop, add the server config:\n\nOn MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\nOn Windows: `%APPDATA%/Claude/claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"langflow-doc-qa-server\": {\n      \"command\": \"node\",\n      \"args\": [\n        \"/path/to/doc-qa-server/build/index.js\"\n      ],\n      \"env\": {\n        \"API_ENDPOINT\": \"http://127.0.0.1:7860/api/v1/run/480ec7b3-29d2-4caa-b03b-e74118f35fac\"\n      }\n    }\n  }\n}\n```","tools":"## Available Tools\n\n1. `query_docs` (Query the document Q&A system, takes a query string as input and returns responses from the Langflow backend)","faq":null,"created_at":"2025-02-23T09:06:44+00:00","updated_at":"2025-03-28T18:00:53+00:00","source_url":"https://model-context-protocol.com/servers/langflow-document-question-answering-mcp-server","related_articles":[]}