bdd-regression-test-generator
MCP server that analyzes OpenAPI/Swagger REST API contracts and generates BDD Gherkin feature files and TypeScript Jest regression test scripts.
README
bdd-regression-test-generator
An autonomous agent that analyzes REST API endpoints and OpenAPI/Swagger service contracts to generate:
- BDD Gherkin specifications (
.featurefiles) describing all happy-path and edge-case scenarios. - TypeScript regression test scripts (Jest + Playwright-ready) ready to run against real services.
It exposes two interfaces:
| Interface | Description |
|---|---|
| CLI | bdd-gen generate --input <spec> --output <dir> |
| MCP Server | Model Context Protocol server exposable to any MCP-aware host (e.g. IBM Bob, Claude Desktop) |
Features
- Parses OpenAPI 3.x and Swagger 2.0 contracts (JSON or YAML).
- Extracts all paths, HTTP methods, parameters, request bodies, and response schemas.
- Generates one
.featurefile per endpoint tag group. - Generates one
*.spec.tsfile per endpoint tag group with fully typed Jest test cases. - Supports custom base-URL injection at generation time.
- MCP server exposes
analyze_contract,generate_gherkin, andgenerate_teststools.
Installation
npm install
npm run build
To use as a global CLI after building:
npm link
CLI Usage
# Generate both Gherkin and Jest tests from an OpenAPI YAML spec
bdd-gen generate --input ./petstore.yaml --output ./generated --baseUrl https://api.example.com
# Generate only Gherkin feature files
bdd-gen generate --input ./petstore.json --output ./generated --only gherkin
# Generate only Jest test scripts
bdd-gen generate --input ./petstore.json --output ./generated --only jest
# Analyze a contract and print a summary (no file generation)
bdd-gen analyze --input ./petstore.yaml
CLI Options
| Option | Alias | Description | Default |
|---|---|---|---|
--input <path> |
-i |
Path to the OpenAPI/Swagger contract file | required |
--output <dir> |
-o |
Directory where generated files will be written | ./generated |
--baseUrl <url> |
-b |
Base URL to embed in the generated test files | http://localhost:3000 |
--only <type> |
Generate only gherkin or jest (omit for both) |
both | |
--verbose |
-v |
Enable verbose logging | false |
MCP Server
Start the MCP server with:
npm run mcp
The server registers the following tools:
analyze_contract
Parses an OpenAPI/Swagger contract from a file path or raw JSON/YAML string.
Input:
{ "source": "./petstore.yaml" }
Output: A structured ContractSummary JSON object with paths, methods, parameters, and schemas.
generate_gherkin
Generates Gherkin .feature content from a parsed contract.
Input:
{
"source": "./petstore.yaml",
"outputDir": "./generated"
}
Output: List of written .feature file paths.
generate_tests
Generates TypeScript Jest test scripts from a parsed contract.
Input:
{
"source": "./petstore.yaml",
"outputDir": "./generated",
"baseUrl": "https://api.example.com"
}
Output: List of written .spec.ts file paths.
Project Structure
bdd-regression-test-generator/
├── src/
│ ├── parser/
│ │ └── contract-analyzer.ts # OpenAPI/Swagger parser and extractor
│ ├── generator/
│ │ ├── gherkin-builder.ts # Gherkin .feature file builder
│ │ └── jest-builder.ts # TypeScript Jest spec builder
│ ├── mcp/
│ │ └── server.ts # MCP server exposing generation tools
│ └── cli.ts # Commander-based CLI entry point
├── tests/
│ └── generator.test.ts # Unit tests for parser and generators
├── dist/ # Compiled output (after build)
├── package.json
├── tsconfig.json
└── README.md
Running Tests
npm test
With coverage:
npm run test:coverage
Example: Generated Gherkin
Feature: Pets
Background:
Given the API base URL is "https://api.example.com"
Scenario: GET /pets - list all pets - success
Given I have valid authentication credentials
When I send a GET request to "/pets"
Then the response status code should be 200
And the response body should match the "PetList" schema
Scenario: GET /pets - list all pets - unauthorized
Given I have invalid or missing authentication credentials
When I send a GET request to "/pets"
Then the response status code should be 401
Example: Generated Jest Test
import axios from 'axios';
const BASE_URL = 'https://api.example.com';
describe('Pets', () => {
describe('GET /pets', () => {
it('should return 200 for a valid request', async () => {
const response = await axios.get(`${BASE_URL}/pets`);
expect(response.status).toBe(200);
});
});
});
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。