MCP Jira Xray Server
Connects to Jira with Xray Test Management to extract test cases related to tickets and list test executions.
README
MCP Jira Xray Server
A Model Context Protocol (MCP) server for extracting test information from Jira Xray. This server connects to Jira instances with Xray Test Management and extracts test cases related to specific tickets.
Features
- š Extract tests related to any Jira ticket
- š List test executions linked to tickets
- šØ Configurable JSON output format
- š¾ Automatic saving to the
extractionsfolder - š Secure connection using Jira API tokens
Installation
Prerequisites
- Node.js 17 or higher
- A Jira instance with Xray Test Management
- Jira API token
Setup
- Clone this repository or install via npm:
git clone <repository-url>
cd mcp-jira-xray
npm install
- Run the interactive setup:
npm run setup
This will guide you through:
- Entering your Jira host URL
- Providing your Jira email
- Adding your API token
- Validating the connection
- Configuring output format
Or manually create a .env file:
cp .env.example .env
# Edit .env with your credentials
Getting a Jira API Token
- Go to Atlassian Account Settings
- Click "Create API token"
- Give it a label and copy the token
- Use this token in your
.envfile
Configuration
Jira Connection
The server requires three configuration values:
JIRA_HOST: Your Jira instance URL (e.g.,https://mycompany.atlassian.net)JIRA_EMAIL: Your Jira account emailJIRA_API_TOKEN: Your Jira API token
Output Format
The OUTPUT_FORMAT environment variable defines the JSON structure for extracted test data. You can customize this to match your needs.
Default format:
{
"ticketId": "",
"test": "",
"testCases": []
}
Custom format example:
{
"ticket": {
"id": "",
"name": ""
},
"tests": {
"cases": []
}
}
The server will populate the fields based on these keys:
ticketIdā The Jira ticket IDtestā The ticket summarytestCasesā Array of test case descriptions
Usage
With VS Code
Good news! The server is already configured for this project in .vscode/mcp.json.
Quick Start:
- Make sure you've run
npm run setup(configuration complete) - Open Command Palette:
Cmd/Ctrl + Shift + P - Type: "MCP: Enable" and press Enter
- Try: "Extract tests for ticket PROJ-123" in Copilot Chat
š See VSCODE-SETUP.md for complete VS Code installation guide
With Claude Desktop
Add this to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"jira-xray": {
"command": "node",
"args": ["/absolute/path/to/mcp-jira-xray/build/index.js"]
}
}
}
Available Tools
1. extract_tests
Extracts all tests related to a given Jira ticket.
Parameters:
ticketId(string): The Jira ticket ID (e.g., "PROJ-123")
Example:
Extract tests for ticket PROJ-123
Output:
- Test execution details
- All test cases with descriptions
- Saved to
extractions/PROJ-123_<timestamp>.json
2. list_test_executions
Lists all test executions linked to a Jira ticket.
Parameters:
ticketId(string): The Jira ticket ID
Example:
List test executions for PROJ-123
Output:
- List of test execution keys
- Test execution summaries
- Execution statuses
Output Files
All extracted test data is saved to the extractions/ folder with the following naming convention:
extractions/<TICKET-ID>_<TIMESTAMP>.json
Example: extractions/PROJ-123_2024-01-15T10-30-45-123Z.json
Development
Interactive Setup
Run the setup wizard:
npm run setup
Validate Configuration
Test your Jira connection:
npm run validate
This will:
- Check your .env configuration
- Test connection to Jira
- Verify authentication
- List accessible projects
- Confirm permissions
Build
npm run build
This compiles TypeScript to JavaScript in the build/ directory.
Project Structure
mcp-jira-xray/
āāā src/
ā āāā index.ts # Main MCP server entry point
ā āāā jira-client.ts # Jira API client
ā āāā config.ts # Configuration management
ā āāā output-handler.ts # File output handling
āāā build/ # Compiled JavaScript (generated)
āāā extractions/ # Output files (generated)
āāā .env # Environment configuration
āāā .env.example # Example configuration
āāā package.json
āāā tsconfig.json
āāā README.md
Troubleshooting
"Missing required environment variables"
Make sure your .env file exists and contains all required variables (JIRA_HOST, JIRA_EMAIL, JIRA_API_TOKEN).
"Failed to get ticket"
- Verify your Jira credentials are correct
- Check that the ticket ID exists in your Jira instance
- Ensure your API token has appropriate permissions
"Xray API not available"
The server tries multiple methods to extract test data. If Xray-specific APIs aren't available, it falls back to standard Jira JQL queries. This may happen if:
- Xray is not installed on your Jira instance
- Your account doesn't have Xray permissions
Connection Issues
- Ensure your
JIRA_HOSTincludes the protocol (https://) - Check that your network allows connections to Jira
- Verify your API token is valid and not expired
License
MIT
Contributing
Contributions are welcome! Please feel free to submit issues or pull requests.
Support
For issues and questions:
- Check existing [GitHub Issues](<repository-url>/issues)
- Create a new issue with detailed information
- Include your Jira and Xray versions
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.