testorax-mcp

Model Context Protocol server for Testorax. Exposes our customer-facing API as MCP tools so Claude / Cursor / any MCP-compatible AI agent can run tests, fetch reports, and manage suites without the user pasting curl commands.

Install

npm install -g testorax-mcp

Configure

The server reads two environment variables:

• TESTORAX_EMAIL (required) — the customer's account email
• TESTORAX_API (optional) — defaults to https://testorax.com

Use with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "testorax": {
      "command": "npx",
      "args": ["-y", "testorax-mcp"],
      "env": {
        "TESTORAX_EMAIL": "[email protected]"
      }
    }
  }
}

Use with Cursor

Add to .cursor/mcp.json in your repo or ~/.cursor/mcp.json globally:

{
  "mcpServers": {
    "testorax": {
      "command": "npx",
      "args": ["-y", "testorax-mcp"],
      "env": {
        "TESTORAX_EMAIL": "[email protected]"
      }
    }
  }
}

Tools

| Tool | What it does | |------|--------------| | list_runs | List recent runs (filter by status) | | run_status | Live status of a specific run | | get_report | Full bug report JSON for a completed run | | create_run | Create a new run; returns runId + payment URL | | list_suites | List saved suites | | run_suite | Trigger a saved suite (charges the saved tier price) | | list_variables | List saved KV variables | | set_variable | Create/update a saved variable | | list_repos | List registered GitHub repos |

Safety notes

• create_run returns a checkoutUrl. The agent should ask the human to complete payment before assuming the run will start.
• run_suite charges immediately because the tier is pre-saved on the suite. Agents should confirm with the human first.
• Read-only tools never expose internal architecture, model names, prompts, or our cost structure.