Langflow Document Q&A Server
Langflow-DOC-QA-服务器
由 Langflow 提供支持的文档问答模型上下文协议服务器
这是一个基于 TypeScript 的 MCP 服务器,实现了一个文档问答系统。它通过提供一个简单的接口来通过 Langflow 后端查询文档,从而演示了 MCP 的核心概念。
先决条件
1. 创建 Langflow 文档问答流程
打开 Langflow 并从“文档问答”模板创建一个新流程
使用必要的组件(ChatInput、File Upload、LLM 等)配置您的流程
保存您的流程
2. 获取 Flow API 端点
点击 Langflow 右上角的“API”按钮
从 cURL 命令复制 API 端点 URL 示例:
http://127.0.0.1:7860/api/v1/run/<flow-id>?stream=falseapi/v1/run/?stream=false保存此 URL,因为
API_ENDPOINT配置需要它
Related MCP server: Chalee MCP RAG
特征
工具
query_docs- 查询文档问答系统将查询字符串作为输入
返回来自 Langflow 后端的响应
发展
安装依赖项:
npm install构建服务器:
npm run build对于使用自动重建的开发:
npm run watch安装
要与 Claude Desktop 一起使用,请添加服务器配置:
在 MacOS 上: ~/Library/Application Support/Claude/claude_desktop_config.json在 Windows 上: %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"
}
}
}
}通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装文档问答服务器:
npx -y @smithery/cli install @GongRzhe/Langflow-DOC-QA-SERVER --client claude环境变量
服务器支持以下环境变量进行配置:
API_ENDPOINT:Langflow API 服务的端点 URL。如果未指定,则默认为http://127.0.0.1:7860/api/v1/run/480ec7b3-29d2-4caa-b03b-e74118f35fac。
调试
由于 MCP 服务器通过 stdio 进行通信,调试起来可能比较困难。我们推荐使用MCP Inspector ,它以包脚本的形式提供:
npm run inspector检查器将提供一个 URL 来访问浏览器中的调试工具。
📜 许可证
该项目已获得 MIT 许可。
Available Tools
1 toolquery_docsC
Query the document Q&A system with a prompt
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'query_docs' has a clear and distinct purpose for querying documents, so agents cannot misselect among multiple options.
The naming is trivially consistent as there is only one tool. It follows a verb_noun pattern ('query_docs'), which is clear and predictable, and there are no other tools to cause inconsistency or mixed conventions.
The tool count is too low for a server with the apparent scope of a 'Document Q&A Server'. A single query tool feels thin and incomplete, as it lacks supporting operations like document upload, management, or retrieval, which are typical for such a domain.
The tool surface is significantly incomplete for a document Q&A system. While 'query_docs' allows querying, there are obvious gaps such as no tools for adding, updating, deleting, or listing documents, which are essential for a functional document management and query workflow.
Maintenance
Related MCP Connectors
Ingest, manage, and retrieve documents for RAG-powered AI applications
Build a RAG pipeline station by station and search your own documents with cited answers.
Query any docs site via MCP. Submit a URL, ask questions, get cited answers.
Query Klaaro datasets, documents, and extracted records from any agent.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables semantic search and question-answering over FAQ documents using RAG (Retrieval-Augmented Generation) with OpenAI embeddings and in-memory vector similarity.-
- AlicenseNot gradedqualityDmaintenanceEnables RAG (Retrieval-Augmented Generation) capabilities with document processing, vector storage, and intelligent Q\&A using OpenAI embeddings and semantic search.MIT
- AlicenseNot gradedqualityCmaintenanceEnables document-based Q&A with multi-modal RAG, hybrid retrieval, knowledge graph reasoning, and multi-agent orchestration via MCP tools.4MIT
- FlicenseNot gradedqualityDmaintenanceEnables querying internal documents via a FastAPI REST API and MCP server, using retrieval-augmented generation and an agentic loop that can invoke tools like document search and calculations.-