Postman MCP Server
Postman MCP 服务器
一个 MCP(模型上下文协议)服务器,支持使用 Newman 运行 Postman 集合。该服务器允许 LLM 执行 API 测试并通过标准化接口获取详细结果。

特征
使用 Newman 运行 Postman 集合
支持环境文件
支持全局变量
详细测试结果包括:
总体成功/失败状态
测试摘要(总计、通过、未通过)
详细故障信息
执行时间
Related MCP server: Postman MCP Server
安装
通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装 Postman Runner:
npx -y @smithery/cli install mcp-postman --client claude手动安装
# Clone the repository
git clone <repository-url>
cd mcp-postman
# Install dependencies
pnpm install
# Build the project
pnpm build用法
配置
将服务器添加到您的 Claude 桌面配置文件~/Library/Application Support/Claude/claude_desktop_config.json :
{
"mcpServers": {
"postman-runner": {
"command": "node",
"args": ["/absolute/path/to/mcp-postman/build/index.js"]
}
}
}可用工具
运行收集
运行 Postman 集合并返回测试结果。
参数:
collection(必需):Postman collection 的路径或 URLenvironment(可选):环境文件的路径或 URLglobals(可选):全局文件的路径或 URLiterationCount(可选):要运行的迭代次数
响应示例:
{
"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
}
}Claude 中的示例用法
您可以通过要求 Claude 中的服务器运行 Postman 集合来使用它:
“在 /path/to/collection.json 运行 Postman 集合并告诉我所有测试是否通过”
克劳德将:
使用运行收集工具
分析测试结果
提供人性化的执行摘要
发展
项目结构
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运行测试
# Run tests
pnpm test
# Run tests with coverage
pnpm test:coverage建筑
# Build the project
pnpm build
# Clean build artifacts
pnpm clean贡献
分叉存储库
创建你的功能分支(
git checkout -b feature/amazing-feature)提交您的更改(
git commit -m 'Add some amazing feature')推送到分支(
git push origin feature/amazing-feature)打开拉取请求
执照
国际学习中心
Available Tools
1 toolrun-collectionC
Run a Postman Collection using Newman
Inputs: collection (required), environment, globals, iterationCount.
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 tool's purpose is clearly defined as running a Postman Collection using Newman, leaving no room for misselection.
The single tool name 'run-collection' follows a clear verb-noun pattern, using a hyphen for separation. Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions.
A single tool is too few for a server named 'Postman MCP Server', which suggests a broader scope related to Postman API testing. This minimal toolset feels thin and underdeveloped, limiting functionality to just running collections without supporting other common Postman operations.
The tool surface is severely incomplete for a Postman-related domain. It only covers running collections, missing obvious gaps such as creating, managing, or listing collections, environments, or variables, which are core to Postman workflows and would cause significant agent failures.
Maintenance
Related MCP Connectors
End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.
Give your AI agents trusted access to the full Postman platform.
Direct access to Cypress tests results and accessibility reports in your AI workflow.
Find your recorded end-to-end web tests, run them and read step-by-step results.
Related MCP Servers
- MIT
- AlicenseBqualityDmaintenanceAn MCP server that enables running Postman collections using Newman, allowing LLMs to execute API tests and get detailed results through a standardized interface.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Postman workspaces, collections, requests, responses, and monitors through the Postman API. Allows users to manage API collections, create and update requests/responses, and execute monitors directly from chat.MIT
- AlicenseBqualityDmaintenanceAutomatically generates Postman collections from code directories by analyzing API endpoints and parameters, enabling easy testing, documentation, and sharing.143MIT