shiptested-mcp

MCP (Model Context Protocol) server for ShipTested. Integrates AI-powered test generation, fixing, and analysis directly into your IDE through Cursor, Claude Code, Claude Desktop, and any MCP-compatible tool.

Quick Start

Install and run via npx:

npx shiptested-mcp

Or install globally:

npm install -g shiptested-mcp

Configuration

All requests are routed through the ShipTested API. Set your API key via the SHIPTESTED_API_KEY environment variable:

SHIPTESTED_API_KEY=sk_live_...
SHIPTESTED_API_URL=https://api.shiptested.app  # optional, this is the default

IDE Configuration

Claude Code

Create a .mcp.json file in your project root:

{
  "mcpServers": {
    "shiptested": {
      "command": "npx",
      "args": ["shiptested-mcp"],
      "env": {
        "SHIPTESTED_API_KEY": "sk_live_..."
      }
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "shiptested": {
      "command": "npx",
      "args": ["shiptested-mcp"],
      "env": {
        "SHIPTESTED_API_KEY": "sk_live_..."
      }
    }
  }
}

Claude Desktop

Add to your Claude Desktop configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "shiptested": {
      "command": "npx",
      "args": ["shiptested-mcp"],
      "env": {
        "SHIPTESTED_API_KEY": "sk_live_..."
      }
    }
  }
}

Do not commit files containing API keys to version control. Use environment variables or add the config file to .gitignore.

Available Tools

analyze_project

Analyze a project's structure, detecting language, framework, test framework, and testable files.

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | projectPath | string | No | Path to the project root. Defaults to cwd. |

list_testable_files

List files in the project that can have tests generated. Optionally filter to only untested files.

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | projectPath | string | No | Path to the project root. Defaults to cwd. | | untestedOnly | boolean | No | If true, only return files without existing tests. |

generate_tests

Generate a test file for a given source file using AI.

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | filePath | string | Yes | Path to the source file to generate tests for. | | projectPath | string | No | Path to the project root. Defaults to cwd. |

fix_tests

Fix a failing test file given the error output.

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | testFilePath | string | Yes | Path to the failing test file. | | errorOutput | string | Yes | The error output from the test runner. | | sourceFilePath | string | Yes | Path to the source file being tested. | | projectPath | string | No | Path to the project root. Defaults to cwd. |

run_tests

Run a test file and return pass/fail status, test counts, and error output.

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | testFilePath | string | Yes | Path to the test file to run. | | projectPath | string | No | Path to the project root. Defaults to cwd. |

generate_and_run

Full test generation loop: generate tests, run them, fix failures, and iterate until they pass.

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | filePaths | string[] | Yes | Array of source file paths to generate tests for. | | projectPath | string | No | Path to the project root. Defaults to cwd. | | maxFixAttempts | number | No | Maximum fix iterations per file. Defaults to 3. |

Available Resources

shiptested://analysis

Returns the current project analysis including language, framework, test framework, testable files, and dependency graph. Results are cached for the session.

shiptested://runs/latest

Returns the latest test run results from the ShipTested dashboard. Only available in proxy mode (requires SHIPTESTED_API_KEY).

Available Prompts

test_strategy

Analyze a source file and suggest a comprehensive testing strategy based on the project context.

| Argument | Type | Description | |----------|------|-------------| | filePath | string | Path to the source file to analyze. |

review_test

Review an existing test file for completeness and correctness by comparing it against its source file.

| Argument | Type | Description | |----------|------|-------------| | testFilePath | string | Path to the test file to review. |

Requirements

• Node.js >= 18
• A ShipTested API key (SHIPTESTED_API_KEY)

License

MIT