Connect AI assistants to testRigor for managing test suites, running tests, viewing results, and automating QA workflows — all through natural language.
The testRigor MCP server provides 14 tools organized into four categories:
| Tool | Description | Key Parameters |
|---|---|---|
list_test_suites |
List all test suites accessible by the authenticated user | (none) |
get_test_suite |
Get metadata for a single test suite (no passwords or API tokens exposed) | testSuiteId |
| Tool | Description | Key Parameters |
|---|---|---|
list_test_cases |
List test cases in a suite (paginated). Supports filtering by label or searching by description | testSuiteId, label?, search?, page?, pageSize? |
get_test_case |
Get a single test case with its full steps | testSuiteId, testCaseUuid |
list_test_case_runs |
List recent run history for a specific test case (most recent first). Returns status, timing, and flowUuid for each run |
testSuiteId, testCaseUuid, page?, pageSize? |
| Tool | Description | Key Parameters |
|---|---|---|
run_test_cases |
Start a test run for specific test cases by UUID (max 100) | testSuiteId, testCaseUuids |
run_green_regression |
Re-run all previously passed (green) test cases from the baseline run | testSuiteId |
execute_supplied_test_steps |
Execute ad-hoc test steps as a new scenario without saving a test case | testSuiteId, steps, scenarioName? |
cancel_task |
Cancel a running task | testSuiteId, taskId |
| Tool | Description | Key Parameters |
|---|---|---|
list_runs |
List test runs for a suite (paginated). Can filter by status | testSuiteId, status?, page?, pageSize? |
get_run |
Get summary and status for a single test run | testSuiteId, taskId |
list_run_test_cases |
List all test case results in a run with status and execution details. Use the returned flowUuid to drill into step-level details |
testSuiteId, taskId, page?, pageSize? |
list_run_failures |
List only the failed and failed-to-start test cases in a run | testSuiteId, taskId, page?, pageSize? |
get_execution_details |
Get per-step execution results with optional screenshot URLs for a test case flow | testSuiteId, taskId, testCaseUuid, flowUuid, includeScreenshots |
Parameters marked with
?are optional.
A typical investigation flow looks like this:
list_test_suites → list_runs → list_run_failures → get_execution_details
To drill into a specific test case:
list_test_cases → get_test_case → list_test_case_runs → get_execution_details
To run tests and monitor results:
run_test_cases → get_run (poll for status) → list_run_test_cases → get_execution_details
You need a Personal Access Token (PAT) to authenticate with the MCP server.
- Log in to testRigor
- Click your name (top-right) → API Tokens
- Click Generate New Token
- Enter a Token Name (e.g.
MCP.TOKEN) - Set Expiration Days (e.g.
180 days) - Click Generate Token
- Copy the token immediately — you will not be able to view it again after closing the dialog
- Store it securely (e.g., in a password manager or environment variable)
- Open Cursor Settings → MCP
- Click Add new global MCP server
- Paste the following into the
mcp.jsonfile:
{
"mcpServers": {
"testrigor": {
"url": "https://api2.testrigor.com/api/v1/mcp",
"headers": {
"personal-access-token": "YOUR_PAT_HERE"
}
}
}
}- Save — Cursor will automatically connect to the server
- You should see testrigor listed with a green indicator and 14 tools available
claude mcp add --transport http testrigor https://api2.testrigor.com/api/v1/mcp \
--header "personal-access-token: YOUR_PAT_HERE"Claude Desktop supports remote MCP servers through the Connectors UI:
- Go to Settings → Connectors
- Click Add Integration
- Enter the MCP server URL:
https://api2.testrigor.com/api/v1/mcp
Note: Claude Desktop connectors have limited support for custom header authentication. If you encounter issues, use the
npx mcp-remotebridge as a workaround:
{
"mcpServers": {
"testrigor": {
"command": "npx",
"args": [
"mcp-remote",
"https://api2.testrigor.com/api/v1/mcp",
"--header",
"personal-access-token: YOUR_PAT_HERE"
]
}
}
}Config file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop after saving.
Edit your MCP config file:
- macOS/Linux:
~/.codeium/windsurf/mcp_config.json - Windows:
%USERPROFILE%\.codeium\windsurf\mcp_config.json
{
"mcpServers": {
"testrigor": {
"serverUrl": "https://api2.testrigor.com/api/v1/mcp",
"headers": {
"personal-access-token": "YOUR_PAT_HERE"
}
}
}
}Note: Windsurf uses
serverUrlinstead ofurlfor remote servers.
Once connected, you can interact with testRigor using natural language. Your AI assistant will automatically choose the right tool.
- "List all my test suites"
- "Show me the test cases in the Login suite"
- "Get the details of the checkout test case"
- "Run the 'login validation' test case in the Smoke Tests suite"
- "Run green regression for the Payment suite"
- "Execute these steps in the Checkout suite: go to url 'https://example.com', click 'Sign In', check that page contains 'Welcome'"
- "Show me the runs for the Login suite"
- "Are there any failures in the latest run?"
- "Show me the step-by-step execution details for the login test case from the latest run"
- "Cancel the running task"
- "What's the status of the current run?"
For MCP server registries and discovery:
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "com.testrigor/mcp-server",
"description": "Manage test suites, run tests, view results, and automate QA workflows via AI with testRigor.",
"version": "1.0.0",
"remotes": [
{
"type": "streamable-http",
"url": "https://api2.testrigor.com/api/v1/mcp",
"headers": [
{
"name": "personal-access-token",
"description": "Your testRigor Personal Access Token (PAT). Generate one at https://app.testrigor.com under Settings > Personal Access Tokens.",
"isSecret": true,
"isRequired": true
}
]
}
]
}- Email: support@testrigor.com
- Website: testrigor.com
- Documentation: testrigor.com/docs