Swagger Testcase MCP

Created By
Eduard Yaushev2 months ago
MCP server for API test case generation from Swagger/OpenAPI specs. Parses Swagger 2.0 and OpenAPI 3.x, generates test cases across 8 categories (positive, negative, boundary, auth, security, idempotency, pagination, business logic), and exports to Postman, TestRail, Allure, k6, pytest, Gherkin, and CSV. Supports internal corporate APIs with auth headers. Auto-saves export files to your working directory.
Overview

What is swagger-testcase-mcp?

swagger-testcase-mcp is an MCP server that automatically generates QA test cases from Swagger/OpenAPI specifications. It analyzes your API spec and produces structured, categorized test cases ready for manual testing or import into your TMS.

How to use swagger-testcase-mcp?

Install via npx in any MCP client (Claude Desktop, Cursor, VS Code, JetBrains, Windsurf):

{
  "mcpServers": {
    "swagger-testcase-mcp": {
      "command": "npx",
      "args": ["-y", "swagger-testcase-mcp"]
    }
  }
}

Then in chat:

  1. "Load the spec from https://petstore3.swagger.io/api/v3/openapi.json"
  2. "Generate test cases for POST /pet"
  3. "Export as postman"

Key features of swagger-testcase-mcp

  • Parses Swagger 2.0 and OpenAPI 3.x (JSON and YAML)
  • Generates test cases across 8 categories: positive, negative, boundary, auth, business logic, security, idempotency, pagination
  • Exports to 9 formats: Markdown, JSON, CSV, Allure CSV, Gherkin, Postman, k6, pytest, TestRail CSV
  • Works with internal corporate APIs behind VPN, SSO, or custom auth
  • Auto-saves exported files to your working directory
  • Validates spec quality with 11 rules and actionable suggestions
  • Compares two spec versions with breaking change detection
  • Generates realistic mock data from schemas with locale support

Use cases of swagger-testcase-mcp

  • Generating baseline test cases for new API endpoints
  • Covering negative, boundary, and security scenarios that often get skipped under deadline pressure
  • Exporting test cases directly to TestRail, Allure TestOps, or Postman
  • Validating OpenAPI spec quality before code review
  • Comparing API versions to detect breaking changes
  • Creating k6 load test scripts or pytest skeletons from specs

FAQ from swagger-testcase-mcp

  • What clients can use swagger-testcase-mcp?

    Any MCP client: Claude Desktop, Cursor, VS Code + Claude Code, VS Code + Cline, JetBrains IDEs, Windsurf.

  • Does it work with internal/private APIs?

    Yes. It supports Bearer tokens, Basic auth, API keys, and custom headers. The server runs locally, so VPN and proxy settings apply automatically.

  • What TMS integrations are supported?

    Allure TestOps (CSV + API), TestRail (Steps and Text templates), Qase, Zephyr Scale, TestLink via generic CSV, and Postman collections.

  • Does it generate business logic test cases?

    It generates test cases based on what is described in the OpenAPI spec. Business rules not in the spec won't be covered automatically, but you can ask the LLM to extend generated cases with your business logic.

Server Config

{
  "mcpServers": {
    "swagger-testcase-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "swagger-testcase-mcp"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
Eduard Yaushev
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago
Crevio

2 days ago