mcp-xray-cloud
An MCP server that connects AI assistants to Xray Cloud for Jira test management, enabling natural language interaction with tests, test plans, executions, and CI result imports.
README
mcp-xray-cloud
An MCP (Model Context Protocol) server that connects AI assistants to Xray Cloud for Jira test management.
Manage tests, test plans, executions, and import CI results — all through natural language via Claude or any MCP-compatible client.
Features
| Category | Tools |
|---|---|
| Tests | list_tests, get_test, create_test, update_test |
| Test Plans | list_test_plans, get_test_plan, create_test_plan, add_tests_to_test_plan |
| Test Executions | list_test_executions, get_test_execution, create_test_execution |
| Test Sets | list_test_sets, get_test_set |
| Test Runs | update_test_run_status |
| Import Results | Xray JSON, Cucumber, JUnit, TestNG, NUnit, Robot Framework, Behave |
| Import Features | Gherkin .feature files |
| Export | Cucumber feature files |
Quick Start
git clone https://github.com/remynln/mcp-xray-cloud.git
cd mcp-xray-cloud
npm install
npm run build
Prerequisites
- Node.js 18+
- An Xray Cloud API key pair (how to generate)
Configuration
Set these environment variables:
| Variable | Required | Description |
|---|---|---|
XRAY_CLIENT_ID |
Yes | Xray Cloud API client ID |
XRAY_CLIENT_SECRET |
Yes | Xray Cloud API client secret |
XRAY_BASE_URL |
No | Override API base URL (default: https://xray.cloud.getxray.app) |
Usage with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"xray": {
"command": "node",
"args": ["/absolute/path/to/mcp-xray-cloud/dist/index.js"],
"env": {
"XRAY_CLIENT_ID": "your-client-id",
"XRAY_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Usage with Claude Code
Add to your .claude.json:
{
"mcpServers": {
"xray": {
"command": "node",
"args": ["/absolute/path/to/mcp-xray-cloud/dist/index.js"],
"env": {
"XRAY_CLIENT_ID": "your-client-id",
"XRAY_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Tool Reference
Tests
- list_tests — List tests with JQL filtering by project, labels, and component
- get_test — Get full test details including steps and preconditions
- create_test — Create Manual, Cucumber, or Generic tests
- update_test — Update test type (Jira field updates require Jira REST API credentials)
Test Plans
- list_test_plans — List test plans in a project
- get_test_plan — Get test plan details with associated tests
- create_test_plan — Create a new test plan
- add_tests_to_test_plan — Associate tests with a test plan
Test Executions
- list_test_executions — List test executions in a project
- get_test_execution — Get execution details with test run statuses
- create_test_execution — Create an execution, optionally linked to a test plan
Test Runs
- update_test_run_status — Set a test run to PASSED, FAILED, TODO, EXECUTING, or ABORTED
Import Results
- import_execution_results — Xray JSON format
- import_cucumber_results — Cucumber JSON
- import_junit_results — JUnit XML
- import_testng_results — TestNG XML
- import_nunit_results — NUnit XML
- import_robot_results — Robot Framework XML
- import_behave_results — Behave JSON
- import_feature_file — Gherkin
.featurefile
Export
- export_cucumber_features — Export Cucumber feature files from Xray tests
Project Structure
src/
├── index.ts # Server entry point
├── client.ts # Xray Cloud API client (auth + GraphQL + REST)
├── helpers.ts # Shared formatting utilities
└── tools/
├── tests.ts # Test CRUD tools
├── test-plans.ts # Test plan tools
├── test-executions.ts# Test execution tools
├── test-sets.ts # Test set tools
├── test-runs.ts # Test run status updates
├── imports.ts # Result import tools (JSON, XML, Gherkin)
└── exports.ts # Feature export tools
Contributing
- Fork the repo
- Create a feature branch (
git checkout -b feat/my-feature) - Run tests (
npm test) - Commit your changes
- Open a pull request
License
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.