Test Automation MCP Server
It gives an AI assistant safe, structured access to configured test suites and JUnit results.
List configured test suites, their commands, and report locations.
Run a configured suite, optionally filtered, and get pass/fail counts plus failing tests.
Summarize the latest JUnit report without re-running.
Get error message, stack trace, and captured output for failing tests by name.
Query JSON test fixtures by exact field values, with a result limit.
File a Jira bug for confirmed defects; without Jira credentials it writes a draft instead.
Per the README, use the
triage_failuresprompt to run, inspect, re-run for flakiness, classify, report, and file bugs only for real defects.Per the README, write shareable investigation reports; note
write_investigation_reportis described but not present in the provided schema.
Supports running configured Appium mobile test suites and parsing their JUnit XML reports to summarize pass/fail results and surface failure details.
Files Jira Cloud bugs with test evidence through the Jira Cloud REST API, falling back to draft files when credentials are not configured.
Supports running configured pytest suites and parsing their JUnit XML output to summarize test results and failures.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Test Automation MCP Server Run the checkout suite and file bugs for any real defects"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Test Automation MCP Server
What it is
A Model Context Protocol server that gives AI assistants (Claude, GitHub Copilot, Cursor) safe, structured access to a test automation stack.
Related MCP server: TestPilot MCP
Why it exists
An assistant in chat usually cannot run a suite, read why tests failed, pull test data, or file a bug with evidence. This server gives it those actions through a small set of defined tools, with safety built in, so an investigation is repeatable and shareable instead of being a one-off chat answer.
Scope and limits
In scope:
Tools:
list_test_suites,run_tests,get_test_results,get_failure_details,query_test_data,write_investigation_report,create_jira_bug(draft file when no Jira credentials are set).Prompt
triage_failures: run, inspect, re-run to rule out flakiness, classify, report, and file bugs only for real defects.Works with any framework that writes JUnit XML.
Out of scope, per the original README:
A built-in Playwright or Appium driver.
Interactive debugging, breakpoints, or live device control.
Other limits from the original README:
This server runs suites you configure in the config file and reads the JUnit XML those suites produce. The examples show a Playwright web suite and an Appium plus TestNG iOS suite because both produce JUnit XML.
Debugging here means inspecting failure details: error message, stack trace, and captured output for a failing test.
create_jira_bugfiles a live Jira issue only when Jira credentials are set. Without them, it writes a draft file toreports/jira-drafts/and reports that no issue was created.An investigation is repeatable through the
triage_failuresprompt, and it is logged and shareable throughwrite_investigation_report, which writes a markdown report toreports/investigations/, plus the JUnit report and the Jira issue or draft.
Features and how it works
From a chat, an assistant can run a suite, read why tests failed, pull test data, write a shareable investigation report, and file a Jira bug with the evidence.
"Run the checkout suite and file bugs for anything that's a real defect."
assistant -> run_tests(sample-e2e) 6 tests: 3 passed, 2 failed, 1 skipped
-> get_failure_details(promo) Expected "$39.20" Received "$49.00" · API: PROMO_EXPIRED
-> run_tests(filter: "order") still times out -> flaky / environment, no bug
-> query_test_data(promoCodes) SPRING10 is marked expired in test data -> test data issue
-> create_jira_bug(...) only for confirmed product defectsTool | What it does |
| Lists configured suites, their commands and report paths |
| Runs a suite (optionally filtered to matching tests) and returns pass/fail counts plus each failure |
| Summarizes the latest JUnit report without re-running |
| Error message, stack trace and captured output for a failing test |
| Looks up accounts, products, promo codes, etc. from a JSON fixture file |
| Writes a shareable markdown report for one triaged test, with its classification, evidence, and action |
| Files a Jira Cloud bug; writes a draft file instead when no credentials are set |
Prompt: triage_failures walks the assistant through run, inspect, re-run to rule out flakiness, classify (product defect, test issue, environment), write an investigation report for each failure, and file bugs only for real defects.
Works with any framework that writes JUnit XML: Playwright, TestNG, Maven Surefire, JUnit 5, pytest and most CI tools all produce JUnit XML, so one parser covers web and mobile suites. See examples/mcp-tests.playwright-and-testng.json for a Playwright web suite next to an Appium + TestNG iOS suite.
Design choices, from the original README:
The model never gets a raw shell. It can only run suites defined in the config file. Test filters are shell-quoted, so a test name cannot inject commands.
Small, model-friendly outputs. Tools return counts and one line per failure; details come only when asked. That keeps context windows small on large suites.
Errors are tool results, not crashes. A bad suite name or a missing report comes back as
isError: truewith a clear message the assistant can act on.Safe by default. Jira writes are drafts until credentials are provided, and read-only tools are annotated
readOnlyHint.
Prerequisites
An environment that can run npm install, npm test and npm run build, as in Quick start below. No other prerequisite is stated in the original README.
Quick start
Install from npm
Package test-automation-mcp-server, version 1.0.0. Use it without cloning, via npx, in Claude Desktop or Claude Code (claude_desktop_config.json / .mcp.json):
{
"mcpServers": {
"test-automation": {
"command": "npx",
"args": ["-y", "test-automation-mcp-server", "/absolute/path/to/mcp-tests.config.json"],
"env": {
"JIRA_BASE_URL": "https://your-company.atlassian.net",
"JIRA_EMAIL": "you@company.com",
"JIRA_API_TOKEN": "..."
}
}
}
}Or install it globally with npm install -g test-automation-mcp-server, then run test-automation-mcp /absolute/path/to/mcp-tests.config.json.
Leave the Jira variables out to keep create_jira_bug in draft mode (drafts go to reports/jira-drafts/).
Install from source
npm install
npm test # 14 tests: JUnit parsing + every tool end to end over an in-memory MCP transport, plus Jira https guard
npm run buildConnect it to Claude Desktop or Claude Code (claude_desktop_config.json / .mcp.json):
{
"mcpServers": {
"test-automation": {
"command": "node",
"args": ["/absolute/path/to/test-automation-mcp-server/dist/index.js", "/absolute/path/to/mcp-tests.config.json"],
"env": {
"JIRA_BASE_URL": "https://your-company.atlassian.net",
"JIRA_EMAIL": "you@company.com",
"JIRA_API_TOKEN": "..."
}
}
}
}Leave the Jira variables out to keep create_jira_bug in draft mode (drafts go to reports/jira-drafts/).
Usage
Configure suites in a config file, for example:
{
"suites": [
{
"name": "web-e2e",
"command": "npx playwright test --reporter=junit",
"cwd": "../my-web-app",
"junitReport": "test-results/junit.xml",
"grepFlag": "--grep"
}
],
"testDataFile": "data/test-data.json",
"jira": { "projectKey": "QA", "issueType": "Bug" }
}Then use the tools listed above, or the triage_failures prompt, to run, inspect, classify, report and, for confirmed product defects only, file a Jira bug.
Testing
npm test # 14 tests: JUnit parsing + every tool end to end over an in-memory MCP transport, plus Jira https guardVerified in CI with a real Android emulator (2026-11-01, GitHub Actions run 41373946277, 1m 57s): a real emulator booted, ApiDemos installed, and run_tests ran 2 tests in 7.3s with 1 passed and 1 failed. The failure was a real UiAutomator2 NoSuchElement error for testMissingElement, and an investigation report was saved. The passing test is identified only by elimination (2 tests total, only testMissingElement failed), not by a named pass line. Jira filing remains draft only without credentials, and Claude or Copilot use has not been tested in a live client session.
Project layout
The original README does not include a project layout table, so none is claimed here. The files named in the original README include the config examples, the JUnit report outputs, reports/investigations/ for investigation reports, and reports/jira-drafts/ for Jira drafts.
Tech
TypeScript · MCP TypeScript SDK · Zod · Vitest · JUnit XML · Jira Cloud REST API
Run with a real model in CI
The original README does not describe a real-model CI workflow for this repo, so none is claimed here.
License
MIT, Copyright (c) 2026 Harika Modali.
Available Tools
6 toolscreate_jira_bugFile a Jira bugA
File a bug for a confirmed product defect. Include reproduction steps, expected vs actual result and the failing test name. Without Jira credentials this writes a draft file instead of creating a real issue.
Inputs: summary (required), description (required), labels, priority.
get_failure_detailsGet failure detailsARead-only
Return the error message, stack trace and captured output for failing tests whose name contains the given text.
Inputs: suite (required), testName (required).
get_test_resultsGet latest resultsBRead-only
Summarize the most recent JUnit report for a suite without re-running it.
Inputs: suite (required).
list_test_suitesList test suitesARead-only
List the test suites this server can run, with their commands and report locations.
Inputs: no named parameters.
query_test_dataQuery test dataARead-only
Look up test accounts, products or other fixtures, filtered by exact field values.
Inputs: entity (required), limit, filter.
run_testsRun a test suiteA
Run a configured test suite (optionally filtered) and return pass/fail counts and the failing tests. Use get_failure_details next to dig into a specific failure.
Inputs: suite (required), filter.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct step in the test workflow: discovering suites, running tests, reading recent results, drilling into failures, querying fixtures, and filing a bug. The run_tests vs. get_test_results distinction is explicit: one executes, the other summarizes an existing report. get_failure_details is also clearly scoped to digging into named failing tests.
All tools use consistent snake_case with a clear verb_noun pattern: list_test_suites, run_tests, get_test_results, get_failure_details, query_test_data, create_jira_bug. The convention is predictable throughout with no mixed styles.
Six tools is well-scoped for a test automation server, covering the core workflow without redundant or filler operations. Each tool has a clear role in the run-inspect-debug-file lifecycle.
The surface covers the main workflow from listing suites through running tests, inspecting failures, querying fixtures, and filing a Jira bug. Minor gaps remain, such as historical results beyond the most recent report and suite configuration/management, but agents can work around them.
Maintenance
Related MCP Connectors
Direct access to Cypress tests results and accessibility reports in your AI workflow.
Test analytics for AI agents: test history, flaky tests, failure clusters, coverage.
The AI orchestration agent for modern software teams.
Write, run and check natural-language browser tests of your web app from your AI assistant.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceConnect AI agents to your test results, insights, and targets. Query test runs, failures, flaky tests, and regressions across frameworks including Playwright, Jest, Pytest, Cypress and more.33 npmMIT- AlicenseNot gradedqualityDmaintenanceEnables AI models (Claude, ChatGPT, GitHub Copilot) to run and analyze local tests, rerun failures, and orchestrate QA workflows using existing UI and API test frameworks.13 npmMIT
- AlicenseAqualityBmaintenanceEnables AI coding assistants to generate, score, run, and auto-heal Playwright E2E tests while enforcing domain-driven page object architecture and anti-flakiness rules.854 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to answer QA questions in a single call, covering run reports, failure grouping by root cause, flaky versus regressed test detection, and coverage gaps. Also exposes raw TestRail API access when a question needs it.MIT