Skip to main content
Glama
enesjakozh
GongRzhe

Langflow Document Q&A Server

by GongRzhe
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Servidor de control de calidad de Langflow DOC

insignia de herrería

Un servidor de protocolo de contexto modelo para preguntas y respuestas sobre documentos impulsado por Langflow

Este es un servidor MCP basado en TypeScript que implementa un sistema de preguntas y respuestas de documentos. Demuestra los conceptos básicos de MCP al proporcionar una interfaz sencilla para consultar documentos a través de un backend de Langflow.

Prerrequisitos

1. Crear un flujo de preguntas y respuestas de documentos de Langflow

  1. Abra Langflow y cree un nuevo flujo a partir de la plantilla "Preguntas y respuestas del documento".

  2. Configure su flujo con los componentes necesarios (ChatInput, carga de archivos, LLM, etc.)

  3. Guarda tu flujo

imagen

2. Obtener el punto final de la API de flujo

  1. Haga clic en el botón "API" en la esquina superior derecha de Langflow

  2. Copie la URL del punto final de la API del comando cURL Ejemplo: http://127.0.0.1:7860/api/v1/run/<flow-id>?stream=false

  3. Guarde esta URL ya que será necesaria para la configuración API_ENDPOINT

imagen

Related MCP server: Chalee MCP RAG

Características

Herramientas

  • query_docs - Consulta el sistema de preguntas y respuestas del documento

    • Toma una cadena de consulta como entrada

    • Devuelve respuestas del backend de Langflow

Desarrollo

Instalar dependencias:

npm install

Construir el servidor:

npm run build

Para desarrollo con reconstrucción automática:

npm run watch

Instalación

Para utilizar con Claude Desktop, agregue la configuración del servidor:

En MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json En 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"
      }
    }
  }
}

imagen

Instalación mediante herrería

Para instalar Document Q&A Server para Claude Desktop automáticamente a través de Smithery :

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

Variables de entorno

El servidor admite las siguientes variables de entorno para la configuración:

  • API_ENDPOINT : La URL del punto final del servicio API de Langflow. El valor predeterminado es http://127.0.0.1:7860/api/v1/run/480ec7b3-29d2-4caa-b03b-e74118f35fac si no se especifica.

Depuración

Dado que los servidores MCP se comunican a través de stdio, la depuración puede ser complicada. Recomendamos usar el Inspector MCP , disponible como script de paquete:

npm run inspector

El Inspector proporcionará una URL para acceder a las herramientas de depuración en su navegador.

📜 Licencia

Este proyecto está licenciado bajo la licencia MIT.

Available Tools

1 tool
query_docsC

Query the document Q&A system with a prompt

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesThe query prompt to search for in the documents

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions querying a 'document Q&A system', which implies a read-only operation, but doesn't specify behavioral traits like response format, error handling, rate limits, or authentication needs. The description is too minimal to provide adequate transparency for safe and effective use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence: 'Query the document Q&A system with a prompt'. It's front-loaded and efficiently conveys the core action without unnecessary words. However, it could be slightly more informative without losing conciseness, such as by specifying the system's purpose or output type.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (a query tool with no annotations and no output schema), the description is incomplete. It lacks details on what the tool returns, how results are formatted, any limitations, or error conditions. Without annotations or an output schema, the description should provide more context to help the agent understand the tool's behavior and outcomes, but it falls short.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the 'query' parameter documented as 'The query prompt to search for in the documents'. The description adds no additional meaning beyond this, as it doesn't elaborate on query syntax, examples, or constraints. With high schema coverage, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool 'Query the document Q&A system with a prompt', which provides a basic verb ('Query') and resource ('document Q&A system'), making the purpose somewhat clear. However, it's vague about what 'document Q&A system' entails and doesn't specify the scope or type of documents, leaving room for ambiguity. Without sibling tools, it doesn't need differentiation, but the purpose could be more specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance on when to use this tool, such as what types of queries it supports, prerequisites, or limitations. It simply states the action without context, leaving the agent to infer usage from the tool name and parameters alone. This lack of explicit or implied guidelines reduces its helpfulness in selecting the tool appropriately.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • First observedquery_docs
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.9/5.0

Scored across 1 tool

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count2/5

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.

Completeness2/5

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

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches