Skip to main content
MCP server CX Codex

Advanced Zebrunner MCP Server — Claude Code MCP server

An MCP server that gives your agent Zebrunner reporting, failure forensics and guarded test-case edits.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add --env ZEBRUNNER_URL=<ZEBRUNNER_URL> --env ZEBRUNNER_LOGIN=<ZEBRUNNER_LOGIN> --env ZEBRUNNER_TOKEN=<ZEBRUNNER_TOKEN> --env TIMEOUT=<TIMEOUT> --env RETRY_ATTEMPTS=<RETRY_ATTEMPTS> --transport stdio advanced-zebrunner-mcp-server -- npx -y mcp-zebrunner
Open on GitHub

What Advanced Zebrunner MCP Server does

The server exposes Zebrunner through its Public API. You get 76 tools registered under the adv_ prefix, resources for @ context injection and slash prompts for common workflows. Because every tool carries the adv_ prefix, nothing collides with the official Zebrunner MCP, and the two can run side by side. Older tool names still resolve as deprecated aliases, so scripts and prompts written against them keep working for now. They disappear in the next major release, which is worth planning for if you rely on them.

Coverage is broad: pass-rate trends and regression stability reports, coverage gap hunting, automation readiness scoring, a rules system for validating test cases, and screenshot or video analysis backed by sharp, ffmpeg and tesseract. Launch and test-run management is included, along with adv_scaffold_test_case for authoring cases and adv_prepare_jira_automation_plan, which turns a Zebrunner suite into a structured Jira plan. Transports and auth cover STDIO, Streamable HTTP, OAuth, Okta SSO and token exchange.

Three environment variables are required: ZEBRUNNER_URL, ZEBRUNNER_LOGIN and ZEBRUNNER_TOKEN. TIMEOUT and RETRY_ATTEMPTS are optional. If your Zebrunner project keys are long, projectAliases in zebrunner-config.json lets tools accept short names instead.

What it helps with

  • pull a regression stability report for a period
  • find coverage gaps across suites
  • score test cases for automation readiness
  • diagnose a failed test from its screenshot or video
  • rerun failed tests inside a launch

Example prompts for the agent

  • Show the pass-rate trend for this project over the last week and flag the suites that dropped
  • Find coverage gaps between suites and suggest what to add
  • Look at the screenshot from the failed test and tell me what went wrong

How to install Advanced Zebrunner MCP Server

Platform CLI

claude mcp add --env ZEBRUNNER_URL=<ZEBRUNNER_URL> --env ZEBRUNNER_LOGIN=<ZEBRUNNER_LOGIN> --env ZEBRUNNER_TOKEN=<ZEBRUNNER_TOKEN> --env TIMEOUT=<TIMEOUT> --env RETRY_ATTEMPTS=<RETRY_ATTEMPTS> --transport stdio advanced-zebrunner-mcp-server -- npx -y mcp-zebrunner

Replace <…> with your own values. 14 more environment variables are in the server README

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Advanced Zebrunner MCP Server

How do I install Advanced Zebrunner MCP Server in Claude Code?

Run `claude mcp add mcp-zebrunner -e ZEBRUNNER_URL=<ZEBRUNNER_URL> -e ZEBRUNNER_LOGIN=<ZEBRUNNER_LOGIN> -e ZEBRUNNER_TOKEN=<ZEBRUNNER_TOKEN> -- npx -y mcp-zebrunner`, replacing the placeholders with your Zebrunner URL, login and token.

What does Advanced Zebrunner MCP Server do?

It hands your agent Zebrunner analytics, reporting, failure investigation and test-case mutations. That means 76 adv_* tools plus resources and slash prompts.

Can it run alongside the official Zebrunner MCP?

Yes. The adv_ prefix keeps tool names from clashing, so both servers can be configured at once.

Similar MCP servers

All MCP servers for Testing and QA →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor