mcp-api-test

An AI-native API testing engine that enables LLM agents to execute, validate, and reason about REST APIs using natural language or cURL inputs.

Unlike traditional testing frameworks, mcp-api-test exposes API testing as a first-class capability for AI agents rather than a developer-facing tool. LLM-powered clients invoke the run_test_api tool directly, making API validation a building block for autonomous coding agents, not a separate human-driven workflow.

It complements (rather than replaces) tools like pytest, Postman, and Playwright.

Use cases

• QA & test engineering: prompt an agent with natural language instead of crafting Postman requests
• Post-deployment regression: have an agent smoke-test critical paths after a deploy
• Quick validation: test an endpoint inline during a coding session
• CI/CD automation: agents validate deployments autonomously in pipelines

Token efficiency. Agents get deterministic, structured results in a single tool call instead of parsing raw curl output. Fewer tokens, fewer hallucinations.

Install

pip install mcp-api-test

Or from source:

git clone git@gitlab.com:ryaneatfood/mcp-api-testing.git
cd mcp-api-testing
pip install -e .

Requires Python >= 3.10.

Quick start

Configure your MCP client to use the server. For OpenCode, add to opencode.json:

{
  "mcp": {
    "mcp-api-test": {
      "type": "local",
      "command": ["mcp-api-test"],
      "enabled": true
    }
  }
}

For Claude Desktop, add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-api-test": {
      "command": "mcp-api-test"
    }
  }
}

Then prompt your agent:

"Test this API: curl -X POST https://api.example.com/v1/users -H 'Authorization: Bearer xxx' -d '{"name":"test"}', ensure status code is 201 and response contains 'id'"

The agent invokes run_test_api, validates against the expected contract, and returns structured pass/fail results.

Documentation

Full documentation is hosted on GitLab Pages (or build locally with mkdocs serve).

• Getting Started: installation and client setup
• Usage: cURL mode, structured mode, assertions, response format
• Guides: troubleshooting, development, configuration
• Reference: full parameter reference

License

MIT