Xray MCP Server

Server MCP untuk plugin manajemen pengujian Xray di Jira. Menghindari masalah kombinasi Jira/Xray yang lambat. Dapat membawa seluruh rangkaian pengujian lebih cepat daripada menambahkan secara manual. Dapat mengintegrasikan pengujian AI karena mampu memperbarui kasus uji juga. Mengapa MCP dan bukan skill? MCP berkomunikasi dengan baik dengan Atlassian MCP.

Dokumentasi

xray-cloud-mcp

An MCP server for Xray Cloud (test management for Jira). It lets an MCP client (Claude Code, Claude Desktop, etc.) import automation results and manage Xray test entities — Tests, Test Executions, and Test Sets — directly.

Tools

ToolAPIRead/WritePurpose
import_execution_junitRESTwriteImport JUnit XML results into a Test Execution
import_execution_xrayRESTwriteImport native Xray-JSON execution results
get_testsGraphQLreadQuery Test issues by JQL
create_testGraphQLwriteCreate a Manual/Cucumber/Generic Test (with steps)
update_testGraphQLwriteChange a Test's type and/or append steps
get_test_executionsGraphQLreadQuery Test Executions by JQL
create_test_executionGraphQLwriteCreate a Test Execution, optionally seeded with tests
add_tests_to_executionGraphQLwriteAdd tests to an existing execution
add_tests_to_test_setGraphQLwriteAdd tests to an existing Test Set

The write tools mutate shared Jira/Xray state — review the target before running them.

Credentials

Create an Xray API Key in Jira → Xray → Global Settings → API Keys (for a service user). This yields a client_id + client_secret. The server resolves them at startup, never from a file on disk, in this order:

  1. Direct env vars XRAY_CLIENT_ID + XRAY_CLIENT_SECRET, if both are set — simplest for local use and CI.
  2. Azure Key Vault — read from the vault at XRAY_KEY_VAULT_URL via DefaultAzureCredential (az login locally, managed identity in Azure). Useful when you don't want secrets in env.

Configuration

VarRequiredDefaultPurpose
XRAY_CLIENT_ID / XRAY_CLIENT_SECRETone of the two methodsDirect credentials
XRAY_KEY_VAULT_URL(if not using direct vars)Azure Key Vault to read secrets from
XRAY_CLIENT_ID_SECRET_NAMEnoxray-client-idKey Vault secret name for the client id
XRAY_CLIENT_SECRET_SECRET_NAMEnoxray-client-secretKey Vault secret name for the client secret
XRAY_BASE_URLnohttps://xray.cloud.getxray.appXray Cloud endpoint

If you only need direct env-var auth, the @azure/* dependencies are still installed but never invoked. Remove them and the Key Vault branch in src/config.ts if you want a leaner build.

Build

npm install
npm run build        # -> dist/
npm run auth-check   # resolves credentials + obtains a token (prints no secret)

Use with an MCP client

Add to your MCP client config (e.g. Claude Code's .mcp.json or Claude Desktop's config), pointing at the built entrypoint:

{
  "mcpServers": {
    "xray": {
      "command": "node",
      "args": ["/absolute/path/to/xray-cloud-mcp/dist/index.js"],
      "env": {
        "XRAY_CLIENT_ID": "your-client-id",
        "XRAY_CLIENT_SECRET": "your-client-secret"
      }
    }
  }
}

Or, with Azure Key Vault instead of inline secrets:

"env": {
  "XRAY_KEY_VAULT_URL": "https://your-vault.vault.azure.net"
}

Notes

  • Description on create: some Jira projects make the Description field mandatory; create_test defaults it to the summary so creation never fails for lack of one.
  • Importing results: point import_execution_junit at the JUnit XML your test runner produces (Playwright, Jest, JUnit, etc.). Use import_execution_xray for the richer native Xray JSON.
  • stdio only: the server speaks MCP over stdio; diagnostics go to stderr (stdout is the protocol channel).

License

MIT — see LICENSE.