Un servidor MCP (Protocolo de Contexto de Modelo) que permite ejecutar colecciones Postman con Newman. Este servidor permite a los LLM ejecutar pruebas de API y obtener resultados detallados mediante una interfaz estandarizada.
Ejecutar colecciones de Postman usando Newman
Soporte para archivos de entorno
Soporte para variables globales
Resultados detallados de las pruebas que incluyen:
Estado general de éxito/fracaso
Resumen de la prueba (total, aprobado, reprobado)
Información detallada sobre fallos
Tiempos de ejecución
Related MCP server: Postman MCP Generator
Para instalar Postman Runner para Claude Desktop automáticamente a través de Smithery :
npx -y @smithery/cli install mcp-postman --client claude# Clone the repository
git clone <repository-url>
cd mcp-postman
# Install dependencies
pnpm install
# Build the project
pnpm buildAgregue el servidor a su archivo de configuración de escritorio Claude en ~/Library/Application Support/Claude/claude_desktop_config.json :
{
"mcpServers": {
"postman-runner": {
"command": "node",
"args": ["/absolute/path/to/mcp-postman/build/index.js"]
}
}
}Ejecuta una colección de Postman y devuelve los resultados de la prueba.
Parámetros:
collection (obligatorio): Ruta o URL a la colección de Postman
environment (opcional): Ruta o URL al archivo de entorno
globals (opcional): Ruta o URL al archivo global
iterationCount (opcional): Número de iteraciones a ejecutar
Ejemplo de respuesta:
{
"success": true,
"summary": {
"total": 5,
"failed": 0,
"passed": 5
},
"failures": [],
"timings": {
"started": "2024-03-14T10:00:00.000Z",
"completed": "2024-03-14T10:00:01.000Z",
"duration": 1000
}
}Puedes usar el servidor en Claude pidiéndole que ejecute una recopilación de Postman:
Ejecute la colección Postman en /path/to/collection.json y dígame si se aprobaron todas las pruebas.
Claude querrá:
Utilice la herramienta de recopilación de ejecuciones
Analizar los resultados de las pruebas
Proporcionar un resumen comprensible de la ejecución.
src/
├── index.ts # Entry point
├── server/
│ ├── server.ts # MCP Server implementation
│ └── types.ts # Type definitions
└── newman/
└── runner.ts # Newman runner implementation
test/
├── server.test.ts # Server tests
├── newman-runner.test.ts # Runner tests
└── fixtures/ # Test fixtures
└── sample-collection.json# Run tests
pnpm test
# Run tests with coverage
pnpm test:coverage# Build the project
pnpm build
# Clean build artifacts
pnpm cleanBifurcar el repositorio
Crea tu rama de funciones ( git checkout -b feature/amazing-feature )
Confirme sus cambios ( git commit -m 'Add some amazing feature' )
Empujar a la rama ( git push origin feature/amazing-feature )
Abrir una solicitud de extracción
ISC
Run a Postman Collection using Newman
| Name | Required | Description | Default |
|---|---|---|---|
| collection | Yes | Path or URL to the Postman collection | |
| environment | No | Optional path or URL to environment file | |
| globals | No | Optional path or URL to globals file | |
| iterationCount | No | Optional number of iterations to run |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure but only states the basic action. It fails to mention critical behavioral traits such as whether this is a read-only or destructive operation, authentication requirements, rate limits, execution time, or what happens during the run (e.g., output format, error handling).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It is appropriately sized and front-loaded, directly stating the tool's purpose without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of running a Postman collection (which involves execution, potential side effects, and output), the lack of annotations and output schema means the description is incomplete. It does not address what the tool returns, error conditions, or behavioral implications, leaving significant gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting all four parameters. The description adds no additional semantic information about parameters beyond what the schema provides, so it meets the baseline of 3 for adequate but not additive value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Run') and the resource ('a Postman Collection using Newman'), providing a specific verb+resource combination. However, since there are no sibling tools mentioned, it cannot demonstrate differentiation from alternatives, which prevents a perfect score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or contextual constraints. It simply states what the tool does without offering any usage instructions or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
run-collectionScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between 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 against. The naming follows a clear verb_noun pattern.
A single tool is too few for a server named 'Postman MCP Server', which suggests broader Postman API functionality. This minimal set feels thin and under-scoped for the implied domain.
The tool surface is severely incomplete for a Postman server. It only allows running collections, missing essential operations like creating/editing collections, managing environments, viewing results, or interacting with other Postman features.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
