qa-ai-mcp-server-gits
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | debug, info, warn, error | |
| GITHUB_REPO | No | Target repository. Required for live bug creation. | |
| GITHUB_OWNER | No | GitHub org or username. Required for live bug creation. | |
| GITHUB_TOKEN | No | GitHub PAT with repo scope. Required for live bug creation. | |
| PLAYWRIGHT_HEADLESS | No | Default headless mode for locator discovery | |
| ALLOW_PRODUCTION_URLS | No | Set 'true' to allow production-like URLs | |
| GITHUB_DEFAULT_LABELS | No | Comma-separated labels (default: bug,automated-test,qa) | bug,automated-test,qa |
| PLAYWRIGHT_TIMEOUT_MS | No | Default Playwright timeout |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_test_scenariosC | Generate comprehensive test scenarios from user stories and acceptance criteria |
| generate_test_casesC | Convert generated scenarios into detailed manual/automation-ready test cases |
| discover_stable_locatorsC | Open the application in Playwright and discover stable locators using accessibility-first priority |
| generate_playwright_testC | Generate a Playwright TypeScript framework with Page Object Model, data files, and utilities |
| run_playwright_testC | Execute Playwright tests and capture results, screenshots, traces, and videos |
| create_bugA | Create a bug ticket from a failed test — supports GitHub Issues, Jira, and Azure DevOps (dry-run or live) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| qa_automation_workflow | Generate a complete prompt to run all qa-ai-mcp-server-gits tools: scenarios → cases → locators → Playwright codegen → test run → bug |
| qa_automation_workflow_example | Pre-filled workflow prompt for Applitools demo login (UserLogin feature) |
| qa_automation_workflow_short | Compact workflow prompt for quick MCP tool chaining |
| qa_automation_instructions | Setup and usage instructions for public npm users |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: bug creation, locator discovery, test generation at multiple levels, and test execution. No two tools can be easily confused.
All tool names follow a consistent verb_noun pattern with underscores (e.g., create_bug, generate_test_cases), making them predictable and easy to understand.
With 6 tools, the server is well-scoped for a QA automation domain, covering essential operations without unnecessary bloat or deficiency.
The tool surface covers the core QA workflow—scenario generation, test case creation, Playwright test generation, execution, and bug reporting. Minor gaps exist (e.g., no tool to list or update bugs), but the set is largely self-contained.