MCP Xray Python

Bridges Jira context with Gemini prompts to auto-create test cases as MCP in Jira/Xray.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mendezangelleo-mcp-xray-python": {
      "command": "python",
      "args": [
        "run_mcp.py",
        "--issue",
        "PROJ-123"
      ],
      "env": {
        "JIRA_URL": "YOUR_JIRA_URL",
        "JIRA_USER": "YOUR_JIRA_EMAIL",
        "JIRA_API_TOKEN": "YOUR_JIRA_API_TOKEN",
        "JIRA_PROJECT_KEY": "PROJ",
        "GEMINI_MODEL_NAME": "gemini-1.5-pro",
        "VERTEX_AI_LOCATION": "us-central1",
        "VERTEX_AI_PROJECT_ID": "YOUR_GCP_PROJECT_ID",
        "GOOGLE_APPLICATION_CREDENTIALS": "PATH/TO/credentials.json"
      }
    }
  }
}

QA Autopilot is an MCP-based CLI that bridges Jira (as your knowledge server) with Google Gemini (via Vertex AI) to generate and create test cases from a user story. It automates context extraction, model prompting, and test creation, freeing you to focus on validation and risk analysis.

How to use

You run the MCP client from your terminal by providing the Jira issue ID. The tool connects to Jira to fetch the story context, sends that context to Gemini to generate a structured set of test cases in Gherkin format, and then creates corresponding Test issues in Jira/Xray linked to the original user story. You simply review, adjust, and approve the generated tests.

How to install

# Prerequisites
Python 3.10+
A Jira Cloud account with Xray installed
Permissions to create API tokens in Atlassian
A Google Cloud project with Vertex AI API enabled and a service account JSON key

# Clone the project
git clone https://github.com/tu-usuario/mcp-xray-python.git
cd mcp-xray-python

# Create and activate a virtual environment
python -m venv venv
# macOS/Linux
source venv/bin/activate
# Windows
.\venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

Configuration and usage notes

The workflow is designed to be straightforward: configure credentials, then run the MCP client with your Jira issue key to generate tests. Ensure your environment variables are correctly set for Jira and Google Vertex AI access.

Additional notes

Prerequisites cover Python 3.10+, Jira Cloud with Xray, and Vertex AI access through a Google Cloud service account JSON key.
Use the provided command examples to generate tests for a specific Jira issue and, if needed, to delete obsolete tests during regeneration.
Generated tests appear in Jira as new Test issues linked to the original story, ready for review.

Available tools

jira_api

Module handling Jira REST API interactions (fetching issues, creating Test issues, linking them to the original HU)

gemini_llm

Module that builds a prompt from Jira context and queries Google Gemini via Vertex AI to generate test cases in Gherkin format

tc_generator

Converter/formatter that structures Gemini responses into a sequence of Gherkin test cases

jira_integration

Orchestrator that creates Jira/Xray Test issues for each generated test case and links them to the source HU

Built by

VeilStrat

AI signals for GTM teams