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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.