SHAFT MCP Server Setup Guide
What is SHAFT MCP?
SHAFT MCP is a Model Context Protocol (MCP) server that enables Claude Desktop to perform web automation tasks using the SHAFT Engine (a Selenium-based test automation framework). This gives Claude powerful browser automation capabilities including:
Core Features
- Browser Control: Launch Chrome, Firefox, Safari, or Edge browsers
- Element Interaction: Click, hover, type, clear, drag-and-drop elements
- AI-Enhanced Element Detection: Find elements by natural language descriptions
- Advanced Actions: JavaScript-based clicks, file uploads, cookie management
- Browser Navigation: URL navigation, back/forward, refresh
- Data Extraction: Get page source, element text, attributes, CSS values
- Test Reporting: Generate detailed Allure test reports
Available MCP Tools
The server provides 25+ tools for web automation:
Browser Management:
driver_initialize- Launch browser (Chrome/Firefox/Safari/Edge)driver_quit- Close browserbrowser_navigate- Navigate to URLbrowser_refresh- Refresh pagebrowser_navigate_back/forward- Browser history navigationbrowser_maximize_window- Maximize browser windowbrowser_set_window_size- Set custom window sizebrowser_fullscreen_window- Set fullscreen mode
Element Interaction:
element_click- Click elements using locators (ID, CSS, XPath, etc.)element_click_ai- Click elements using AI (natural language)element_click_js- JavaScript-based clickingelement_double_click- Double-click elementselement_hover- Hover over elementselement_type- Type text into elementselement_type_ai- Type using AI element detectionelement_append_text- Append text to existing contentelement_clear- Clear text from input fieldselement_drag_and_drop- Drag and drop between elementselement_drop_file_to_upload- File upload functionality
Data Extraction:
element_get_text- Get element text contentelement_get_dom_attribute- Get DOM attributeselement_get_dom_property- Get DOM propertieselement_get_css_value- Get CSS property valueselement_is_displayed/enabled/selected- Check element statesbrowser_get_page_source- Get page HTML sourcebrowser_get_current_url- Get current URLbrowser_get_title- Get page title
Session Management:
browser_add_cookie- Add cookiesbrowser_get_cookie- Get specific cookiebrowser_get_all_cookies- Get all cookiesbrowser_delete_cookie- Delete specific cookiebrowser_delete_all_cookies- Clear all cookiesgenerate_test_report- Generate Allure test reports
Distribution
SHAFT MCP is available through multiple channels:
- GitHub MCP Registry: Officially listed in the Model Context Protocol Registry as
io.github.ShaftHQ/shaft-mcp - Maven Central: Available as a Java JAR at
io.github.shafthq:SHAFT_MCP - GitHub Container Registry: Docker images available at
ghcr.io/shafthq/shaft-mcp - Smithery.ai: Deploy via Smithery for hosted MCP server (see SMITHERY_DEPLOYMENT.md)
Deployment Options
SHAFT MCP supports two deployment modes:
1. Local Deployment (Claude Desktop)
Uses STDIO transport for direct integration with Claude Desktop application. See setup instructions below.
2. Remote Deployment (Smithery & Web)
Uses HTTP/SSE transport for web-based access and remote hosting platforms like Smithery.ai, Railway, Render, etc.
📖 For Smithery and remote deployment instructions, see the comprehensive Smithery Deployment Guide which includes:
- Step-by-step Smithery deployment
- Local testing with Docker
- 10+ alternative hosting platforms comparison
- Configuration options and best practices
Prerequisites
- Claude Desktop App (latest version)
- Java 21 (OpenJDK 21.0.2 LTS or newer) - for JAR-based installation
- OR Docker - for Docker-based installation
- Maven (only if building from source)
Setup Instructions
You can install SHAFT MCP using either the JAR file or Docker container:
Option A: Using Docker (Recommended)
-
Close Claude Desktop completely if it's running
-
Pull the Docker image:
docker pull ghcr.io/shafthq/shaft-mcp:latest
-
Locate your Claude config file:
- Windows:
C:\Users\{USERNAME}\AppData\Roaming\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- Windows:
-
Edit the config file and add the SHAFT MCP server configuration:
{
"mcpServers": {
"shaft-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/shafthq/shaft-mcp:latest"
]
}
}
}
Option B: Using JAR File
Step 1: Build the MCP Server
- Navigate to your SHAFT_MCP repository directory:
cd /path/to/ShaftHQ/SHAFT_MCP
- Build the project (this creates the JAR file):
mvn clean package -DskipTests -Dgpg.skip
This will create: target/SHAFT_MCP-9.4.20251108.jar
Step 2: Configure Claude Desktop
-
Close Claude Desktop completely if it's running
-
Locate your Claude config file:
- Windows:
C:\Users\{USERNAME}\AppData\Roaming\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- Windows:
-
Edit the config file and add the SHAFT MCP server configuration:
{
"mcpServers": {
"shaft-mcp": {
"command": "java",
"args": [
"-jar",
"/FULL/PATH/TO/SHAFT_MCP/target/SHAFT_MCP-9.4.20251108.jar"
]
}
}
}
Important Notes:
- Replace
/FULL/PATH/TO/SHAFT_MCP/with the actual absolute path to your repository - Ensure the JAR file version matches what was built (check the
target/directory) - Use forward slashes
/even on Windows, or double backslashes\\\\for Windows paths
Verify Installation
-
Start Claude Desktop
-
Check MCP Server Status:
- Go to
File > Settings > Developer - Look for
shaft-mcpin the MCP servers list - Confirm the status shows as
running
- Go to
-
Test the server with this prompt in Claude:
Use shaft-mcp to launch Chrome, navigate to google.com, search for "selenium webdriver", and get the page title.
Usage Examples
Once configured, you can use Claude to perform complex web automation tasks:
Basic Browser Control
Use shaft-mcp to:
1. Launch Firefox browser
2. Navigate to https://example.com
3. Get the page title and current URL
Element Interaction
Use shaft-mcp to:
1. Launch Chrome
2. Go to a login page
3. Find the username field and type "testuser"
4. Find the password field and type "testpass"
5. Click the login button
AI-Enhanced Element Detection
Use shaft-mcp to:
1. Open a browser and go to amazon.com
2. Click on the search box using AI
3. Type "laptop" in the search field
4. Click the search button using AI
Data Extraction
Use shaft-mcp to:
1. Navigate to a news website
2. Get all the article headlines
3. Extract the main content text
4. Generate a test report
Troubleshooting
Common Issues:
-
"No active browser session found"
- Always initialize a browser first using
driver_initialize
- Always initialize a browser first using
-
MCP Server not running
- Verify the JAR file path is correct and absolute
- Check that Java 21 is installed and accessible
- Ensure Claude Desktop was restarted after config changes
-
Build failures
- Verify Java 21 is installed:
java -version - Ensure Maven is available:
mvn -version - Try cleaning first:
mvn clean
- Verify Java 21 is installed:
-
Element not found errors
- Use AI-based element detection (
element_click_ai,element_type_ai) - Try different locator strategies (CSS, XPath, ID, etc.)
- Check if the element is visible with
element_is_displayed
- Use AI-based element detection (
Advanced Configuration
You can add additional MCP servers alongside SHAFT MCP:
{
"mcpServers": {
"shaft-mcp": {
"command": "java",
"args": ["-jar", "/path/to/SHAFT_MCP-9.4.20251108.jar"]
},
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your_token_here"
}
}
}
}
What This Enables
With SHAFT MCP configured, Claude can:
- Automate web testing - Run comprehensive test suites on web applications
- Perform web scraping - Extract data from websites with complex interactions
- Automate repetitive tasks - Fill forms, upload files, navigate workflows
- Generate test reports - Create detailed Allure reports with screenshots and logs
- Cross-browser testing - Test across Chrome, Firefox, Safari, and Edge
- AI-powered element detection - Find elements by description instead of technical locators
This essentially turns Claude into a powerful web automation assistant that can handle complex browser-based tasks that would normally require manual effort or custom scripting.