Postman Tool Generation MCP Server
Servidor MCP de generación de herramientas Postman
Un servidor MCP que genera herramientas de agente de IA a partir de colecciones y solicitudes de Postman. Este servidor se integra con la API de Postman para convertir los puntos finales de la API en código con seguridad de tipos compatible con diversos frameworks de IA.
El Protocolo de Contexto de Modelo (MCP) es un nuevo protocolo estandarizado para gestionar el contexto entre grandes modelos de lenguaje (LLM) y sistemas externos. En este repositorio, proporcionamos un instalador y un servidor MCP para la API de generación de herramientas Postman .
Esto le permite usar Claude Desktop , o cualquier cliente MCP como Cline , para usar lenguaje natural para lograr cosas en su cuenta de Postman, por ejemplo:
Create an AI tool for: collectionID: 12345-abcde requestID: 67890-fghij typescript openai
Características
Generar código TypeScript/JavaScript a partir de colecciones de Postman
Compatibilidad con múltiples marcos de IA (OpenAI, Mistral, Gemini, Anthropic, LangChain, AutoGen)
Generación de código con seguridad de tipos
Manejo de errores y validación de respuestas
Related MCP server: Postman MCP Generator
Manifestación
Configuración
Instalar dependencias:
npm installConstruir el servidor:
npm run buildConfigure los ajustes de MCP agregando lo siguiente a su archivo de configuración de Claude (
cline_mcp_settings.json):
{
"mcpServers": {
"postman-ai-tools": {
"command": "node",
"args": [
"/path/to/postman-tool-generation-server/build/index.js"
],
"env": {
"POSTMAN_API_KEY": "your-postman-api-key"
},
"disabled": false,
"autoApprove": []
}
}
}Uso
El servidor proporciona una única herramienta llamada generate_ai_tool con los siguientes parámetros:
{
collectionId: string; // The Public API Network collection ID
requestId: string; // The public request ID
language: "javascript" | "typescript"; // Programming language to use
agentFramework: "openai" | "mistral" | "gemini" | "anthropic" | "langchain" | "autogen"; // AI framework
}Ejemplo
// Using the tool through MCP
const result = await use_mcp_tool({
server_name: "postman-ai-tools",
tool_name: "generate_ai_tool",
arguments: {
collectionId: "your-collection-id",
requestId: "your-request-id",
language: "typescript",
agentFramework: "openai"
}
});Código generado
La herramienta genera código seguro que incluye:
Definiciones de tipos para solicitud/respuesta
Manejo de errores
Integración de API
Definiciones de funciones de OpenAI
Documentación y ejemplos
Desarrollo
Instalar dependencias:
npm installRealizar cambios en
src/index.tsConstruir el servidor:
npm run buildReinicie la aplicación Claude para cargar el servidor actualizado
Variables de entorno
POSTMAN_API_KEY: Su clave API de Postman (obligatoria)
Manejo de errores
El servidor incluye un manejo integral de errores para:
Parámetros no válidos
Fallos de API
Errores de análisis de JSON
Problemas de red
Las respuestas de error incluyen mensajes detallados para ayudar a diagnosticar problemas.
Contribuyendo
¡Agradecemos sus contribuciones! No dude en enviar una solicitud de incorporación de cambios.
Licencia
Licencia MIT
Available Tools
1 toolgenerate_ai_toolB
Generate code for an AI agent tool using a Postman collection and request
Inputs: collectionId (required), requestId (required), language (required), agentFramework (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 with other tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against for patterns or conventions.
One tool is too few for the server's stated purpose of 'Postman Tool Generation,' which implies a broader scope like generating, managing, or testing tools. A single generation tool feels thin and incomplete for this domain.
The tool surface is severely incomplete for the inferred domain of Postman-based tool generation. There are obvious gaps, such as no tools for listing, editing, deleting, or testing generated tools, which limits agent workflows to a single action.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAutomatically converts Postman API collections into MCP-compatible tools for AI assistants. Enables users to interact with any API through natural language by generating JavaScript tools from Postman requests.MIT
- AlicenseNot gradedqualityDmaintenanceGenerates MCP servers from Postman API requests, automatically creating JavaScript tools that enable LLMs to interact with any API documented in Postman collections. Supports authentication configuration and deployment via STDIO or SSE.MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that converts Postman API requests into executable tools for LLMs using the Postman Runtime. It supports complex authentication types and enables seamless integration between Postman collections and MCP clients like Claude Desktop.MIT
- AlicenseBqualityCmaintenanceA Model Context Protocol (MCP) server that provides seamless integration with the Postman API, enabling AI assistants and applications to interact with Postman workspaces, collections, requests, environments, and folders programmatically.1927 npm31MIT