API Test MCP 8338532e

MCP开发工具

提供方 GalaxyXieyu

开发工具 stdio · 本地进程 Token 社区 / 第三方 ClaudeCursor
查看接入方式

一个基于YAML声明的API测试框架,专为AI编码助手优化,支持API工作流编排、变量解析引擎和自动认证等功能。

一句话选型结论

按资料字段整理

API Test MCP 8338532e 属于开发工具类 MCP 服务器,stdio · 本地进程,Token,可直接接入 Claude、Cursor,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式stdio · 本地进程 鉴权Token 部署方式本地部署
GitHub 星标 24 仓库热度,无公开仓库时显示未标注
工具数 9 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量9暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

API测试Python本地部署YAML声明自动化测试AI集成测试框架

安装与配置

stdio · 本地进程 Token
客户端在本机拉起子进程,数据不出本机
uvx --from git+https://github.com/GalaxyXieyu/Api-Test-MCP.git api-auto-test-mcp --help

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Python,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 9 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 9 个工具,职责相对集中,接入后不容易误操作。
  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好Token对应的凭据,并按最小权限配置。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
API Test MCP 8338532e当前 9 stdio · 本地进程 本地部署 有 2026-05-17
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方GalaxyXieyu上游标注的维护方 GalaxyXieyu
分类开发工具本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式Token远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · Python本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

9.6 KB
来自项目仓库与上游目录的原文,未做删改

API Auto Test Framework

YAML Declarative API Testing Framework, Optimized for AI Coding Assistants

Case study · AgentsGalaxy · GitHub


Why This Framework?

When asking AI to write API tests, you might encounter these issues:

Scenario 1: Repetitive Work

Every time you ask AI to generate tests, you need to re-describe the project structure, authentication method, and assertion style. For 10 API tests, the same fixture and setup code gets generated 10 times.

Scenario 2: Token Black Hole

A simple login API test generates 200 lines of code. You find an assertion is wrong, ask AI to fix it, and it generates another 200 lines. After 3 revisions, you've consumed 2000+ Tokens, and you still end up fixing it manually.

Scenario 3: Debugging Dead Loop

AI-generated tests fail to run. You paste the error message, AI fixes it but still wrong. After 5 rounds of conversation, the problem persists, and you've burned 5000+ Tokens.

This Framework's Solution:```
Traditional: Natural Language -> AI Generates Full Code -> Run Error -> Paste Error -> AI Regenerates -> Loop...
This Framework: Natural Language -> AI Generates YAML -> Framework Executes -> Locate Issue -> Fix 1 Line YAML


| Metric | Traditional AI | This Framework |
|--------|---------------|----------------|
| Test 1 API | ~200 lines code | ~20 lines YAML |
| Modify Assertion | Regenerate all code | Fix 1-2 lines YAML |
| 10 API Tests | Repeat setup 10x | Shared config, 0 repeat |
| Debug Issue | 3-5 rounds avg | Usually 1 round |

---

## Key Features

| Feature | Description |
|---------|-------------|
| **YAML Declarative Tests** | Test logic separated from execution code, AI generates structured data only |
| **MCP Server** | Seamless integration with Claude/Cursor and other AI editors |
| **API Workflow Orchestration** | Multi-step API calls in single file, with data passing and assertions between steps |
| **Variable Resolution Engine** | Support for cross-step data transfer, global variables, and dynamic function calls |
| **Auto Authentication** | Token acquisition and refresh handled by framework |
| **Data Factory** | Built-in mock data generation, no Java dependencies |
| **Multi-format Reports** | Allure (offline/online), pytest-html (standalone HTML, styled) |
| **Multi-channel Notifications** | DingTalk, Feishu, WeCom |
| **Unit Testing** | Python code unit testing with automatic mock dependency injection |

---

## Quick Start

### Installation```bash
# 1. Install uv (if not installed)
curl -LsSf https://astral.sh/uv/install.sh | sh

# 2. Install MCP server (recommended: install as a tool)
uv tool install git+https://github.com/GalaxyXieyu/Api-Test-MCP.git

# Verify
api-auto-test-mcp --help

# Manage tools
uv tool list
uv tool uninstall api-auto-test   # use the tool name shown by `uv tool list`

Run without installing (uvx):```bash
uvx --from git+https://github.com/GalaxyXieyu/Api-Test-MCP.git api-auto-test-mcp --help


**Common mistake:** `uvx install ...` is **wrong**. `uvx` treats the first word after it as the tool name, so it will try to resolve a package literally named `install` and fail.

### Configure Editor

Add the following to your editor's MCP settings:```json
{
  "mcpServers": {
    "api-auto-test": {
      "command": "api-auto-test-mcp"
    }
  }
}
Editor Config Location
Claude Desktop ~/Library/Application Support/Claude/claude_desktop_config.json
Cursor Settings -> MCP Servers
VSCode + Continue .vscode/mcp.json

Local Development```bash

Recommended with uv

uv pip install -r requirements.txt

Or with pip

pip install -r requirements.txt


### Create Test Case```yaml
# tests/cases/user_login.yaml
testcase:
  name: user_login
  description: User login API test
  host: http://localhost:8000
  steps:
    - id: login
      path: /api/auth/login
      method: POST
      data:
        username: "test_user"
        password: "123456"
      assert:
        - type: status_code
          expected: 200
        - type: equals
          field: data.code
          expected: 0

Generate and Run```bash

Generate pytest scripts

python -m atf.case_generator

Run tests

pytest tests/scripts/ -v

Generate Allure report

pytest tests/scripts/ --alluredir=tests/allure-results
allure serve tests/allure-results

Generate pytest-html report

pytest tests/scripts/ --html=report.html


---

## MCP Server Integration

Through MCP, AI editors can directly call framework tools to generate and execute tests.

### Efficiency Comparison

| Metric | Without MCP | With MCP | Improvement |
|--------|-------------|----------|-------------|
| Total Cost | $0.0214 | $0.0099 | **-54%** |
| API Latency | 11 sec | 4 sec | **-64%** |
| Output Tokens | 585 | 238 | **-59%** |
| Cache Read | 42.0k | 21.0k | **-50%** |

**Test Scenario**: Same API test generation task (pure consultation/analysis conversation)

**Core Advantages**:
- **54% cost reduction**: MCP directly calls tools, avoiding lengthy code generation context
- **64% faster API response**: Tool calls are more efficient than natural language interaction
- **59% less token consumption**: Only necessary parameters needed, no need to repeat project structure

### Available Tools

| Tool | Description |
|------|-------------|
| `list_testcases` | List test cases |
| `get_testcase` | Read test case content |
| `write_testcase` | Create/update test case and generate pytest script |
| `write_unittest` | Create unit test |
| `delete_testcase` | Delete test case |
| `run_tests` | Execute tests |
| `get_test_results` | Get test execution history |
| `health_check` | Service health check |

### Usage Example

Tell AI:```
Create a test for /api/users interface, verify returned user list length > 0

AI will call write_testcase to generate YAML and corresponding pytest script.


Project Structure```

api-auto-test/
├── atf/ # Framework core
│ ├── core/ # Request, assertion, variable resolution modules
│ ├── mcp/ # MCP Server implementation
│ └── handlers/ # Notification, report handlers
├── tests/
│ ├── cases/ # YAML test cases
│ └── scripts/ # Generated pytest scripts
├── config.yaml # Project config (environment, database, notifications)
└── pyproject.toml


---

## YAML Test Case Spec

### Basic Structure```yaml
testcase:
  name: test_name              # Case name, used for filename
  description: Description     # Optional
  host: http://localhost:8000  # API host, can also be configured globally in config.yaml
  steps:
    - id: step1                # Step ID, used for later reference
      path: /api/endpoint
      method: POST
      headers:
        Authorization: "Bearer {{ login.data.token }}"  # Reference response from other step
      data:
        key: value
      assert:
        - type: status_code
          expected: 200
        - type: equals
          field: data.id
          expected: 1

Assertion Types

Type Description Example
status_code HTTP status code expected: 200
equals Exact match field: data.id, expected: 1
contains Contains field: data.name, expected: "test"
length Array/string length field: data.list, expected: 10
regex Regex match field: data.email, expected: "^\\w+@"

Variable Reference```yaml

Reference response data from other steps

token: "{{ login.data.token }}"

Reference global config

host: "{{ merchant.host }}"

Call built-in functions

timestamp: "{{ tools.get_timestamp() }}"
uuid: "{{ tools.generate_uuid() }}"


### Teardown```yaml
testcase:
  name: create_and_delete_user
  steps:
    - id: create_user
      path: /api/users
      method: POST
      data:
        name: "test_user"
  teardowns:
    - id: delete_user
      operation_type: api
      path: /api/users/{{ create_user.data.id }}
      method: DELETE

Unit Testing

Support for writing unit tests for Python code, automatically generating test cases through MCP tools.

Unit Test YAML Format```yaml

unittest:
name: UserService Test
target:
module: app.services.user_service
class: UserService
function: get_user
fixtures:
setup:
- type: patch
target: app.services.user_service.UserRepository
return_value:
id: 1
name: "test_user"
cases:
- id: test_get_user_success
description: Test get user success
inputs:
args: [1]
kwargs: {}
assert:
- type: equals
field: result.id
expected: 1
- type: equals
field: result.name
expected: "test_user"


### Assertion Types

| Type | Description |
|------|-------------|
| `equals` | Exact match |
| `not_equals` | Not equal |
| `contains` | Contains |
| `raises` | Expect exception to be raised |
| `is_none` | Result is None |
| `is_not_none` | Result is not None |
| `called_once` | Mock called once |
| `called_with` | Mock called with specific arguments |

---

## Configuration File```yaml
# config.yaml
projects:
  merchant:
    test:
      host: http://192.168.1.100:8080
      is_need_login: true
      login:
        url: http://192.168.1.100:8080/login
        method: POST
        data:
          username: admin
          password: "123456"
    online:
      host: https://api.example.com
      is_need_login: true

notifications:
  dingtalk:
    webhook: "https://oapi.dingtalk.com/robot/send?access_token=xxx"
    secret: "SECxxx"

License

MIT License


Links

  • GitHub
  • Issue Report

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
API Test MCP 8338532e 怎么安装?

在客户端按下面的安装命令接入:uvx --from git+https://github.com/GalaxyXieyu/Api-Test-MCP.git api-auto-test-mcp --help。装完在客户端配置里引用同一个包或端点。

API Test MCP 8338532e 怎么在 Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

API Test MCP 8338532e 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

API Test MCP 8338532e 需要 API Key 吗?

资料标注需要Token认证,使用前准备好对应凭据,并按最小权限配置。

API Test MCP 8338532e 支持哪些客户端?

资料标注支持 Claude、Cursor;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

API Test MCP 8338532e 能提供哪些能力?

资料显示约 9 个工具;能力标签包括 API测试、测试框架、Python、Claude、自动化测试。具体工具清单以官方文档为准。

API Test MCP 8338532e 需要什么运行环境?

运行时为 Python;属于本地进程,需要在本机装好运行环境。

API Test MCP 8338532e 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。