mcpField
S
shaft-mcp

shaft-mcp

Local
shafthq.github.ioBrowser Automation416Updated today

About shaft-mcp

SHAFT is a Java automation engine for test teams, using one API for web, mobile, API, CLI, database, and desktop tests. It manages drivers and waits, then produces an Allure report with steps, screenshots, and logs for each run.

Key features

  1. 01One API for multiple testing surfaces
  2. 02Managed Selenium and Appium drivers
  3. 03Synchronized actions and smart waits
  4. 04Allure reports with steps, screenshots, and logs
  5. 05Runs locally or with Grid, BrowserStack, and LambdaTest

Use cases

  1. 01Test web and mobile in one project
  2. 02Write REST or GraphQL API tests
  3. 03Run CLI, database, or desktop tests
  4. 04Inspect test steps and evidence in Allure

MCP support

The README mentions MCP tools for AI agents but does not specify which capabilities the MCP server exposes.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"shafthq-shaft": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/shafthq/shaft-engine-mcp:10.4.20261024"
]
}
}
}
Run commanddocker run -i --rm ghcr.io/shafthq/shaft-engine-mcp:10.4.20261024

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocighcr.io/shafthq/shaft-engine-mcp:10.4.20261024

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README
SHAFT logo

Write the test. SHAFT does the rest.

One Java engine for web, mobile, API, CLI, database, and desktop.
Drivers, waits, and evidence are handled. Every run ends in an Allure report.

Read the User Guide   Star SHAFT on GitHub

Maven Central Build OpenSSF Scorecard Codecov

SHAFT in action: a 3-line test, mvn test passing, and the green Allure report it produces.

Upgrade to SHAFT_ENGINE · ▶ Watch the 26-second clip with sound and captions · 100-second overview

Why SHAFT

  • No plumbing. Managed Selenium and Appium drivers, synchronized actions, and smart waits.
  • One fluent API. Web, mobile, REST/GraphQL, database, CLI, and desktop in the same test.
  • Evidence by default. Steps, screenshots, and logs land in an Allure report on every run.
  • Scale by configuration. Local, Grid, BrowserStack, or LambdaTest; TestNG, JUnit, or Cucumber.
  • Open and trusted. MIT licensed, on Maven Central, with an OpenSSF Scorecard and public coverage.

How it works

Test intent and configuration enter SHAFT's orchestration layer, fan out across the execution surfaces you need, and come back as unified evidence.

flowchart LR
    accTitle: SHAFT execution and evidence workflow
    accDescr: Test intent and configuration enter SHAFT orchestration, run across Web, Mobile, API, and Native execution surfaces, and produce unified evidence.
    I[Test intent] --> S[SHAFT orchestration]
    C[Configuration] --> S
    S --> W[Web]
    S --> M[Mobile]
    S --> A[API]
    S --> N[Native, CLI, and Database]
    W --> E[Unified evidence]
    M --> E
    A --> E
    N --> E

Quickstart

Generate your first project and run mvn test. Already on Maven? Add io.github.shafthq:shaft-engine (version from the Maven Central badge):

<dependency>
    <groupId>io.github.shafthq</groupId>
    <artifactId>shaft-engine</artifactId>
    <version>${shaft.version}</version>
</dependency>

Then write the test:

SHAFT.GUI.WebDriver driver = new SHAFT.GUI.WebDriver();
driver.browser().navigateToURL("https://shafthq.github.io/")
      .and().element().assertThat(By.cssSelector("h1")).isVisible();
driver.quit();

Run mvn test. The Allure report opens with every step, screenshot, and log.

Where to next

If SHAFT saves your team time, star the repo. It helps other testers find it.

Star SHAFT on GitHub


Open an issue · Code of Conduct · Security · Sponsor

BrowserStack, LambdaTest, Applitools, and JetBrains have provided tooling or open-source program support. This is support for the project, not a claim of financial sponsorship, customer status, or endorsement.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.