Playwright Report Mcp
Built for AI agents analyzing test failures after the fact, not driving browsers. This server runs your Playwright test suite via `run_tests`, reads the JSON reporter output, and surfaces only what matters: failed test details, error messages, and attachment content through `get_failed_tests` and `get_test_attachment`. The token savings are real: fetching failures from an existing run costs around 300 tokens versus 12,000+ for parsing the full results.json yourself. Designed for CI workflows where tests already ran and you need structured failure data without re-running or parsing megabytes of HTML reports. Requires the Playwright JSON reporter configured in your project.
- tools
- 5
- transport
- STDIO
- env vars
- 2
- last updated
- Sep 25, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
run_testsRuns the Playwright test suite and returns structured pass/fail results.
Runs the Playwright test suite and returns structured pass/fail results.
No parameter schema in public metadata yet.
get_run_statusReturns the current status for a non-blocking run started by `run_tests` with `wait: false`.
Returns the current status for a non-blocking run started by `run_tests` with `wait: false`.
No parameter schema in public metadata yet.
get_failed_testsReturns failed tests from the last run with error messages and attachment paths.
Returns failed tests from the last run with error messages and attachment paths.
No parameter schema in public metadata yet.
get_test_attachmentReads the content of a named text attachment for a specific test from the last run.
Reads the content of a named text attachment for a specific test from the last run.
No parameter schema in public metadata yet.
list_testsLists all tests with their spec file and tags without running them.
Lists all tests with their spec file and tags without running them.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
PW_ALLOWED_DIRSpath.delimiter-separated list of directories the per-call workingDirectory parameter may point at. Entries may be absolute or relative (resolved once against the server's launch cwd at startup). Defaults to '.' (authorizes only the launch directory).
PW_RESULTS_FILEAbsolute path override for the JSON reporter output file. Defaults to <workingDirectory>/test-results/results.json, computed per call.
Readme
Playwright Report MCP
An MCP (Model Context Protocol) server for running Playwright tests and reading structured results, failed test details, and attachment content — designed for AI agents doing test failure analysis.
Table of contents
- What it is
- What it is NOT
- Why
- Quick start
- Tools
- Attachments
- Installation
- Configuration
- Requirements
- Troubleshooting
- Development
- Cutting a release
- Contributing
- Release
- License
What it is
Playwright Report MCP gives an AI agent structured, token-efficient access to Playwright test outcomes. It runs your test suite, reads the JSON reporter output, and surfaces exactly what the agent needs: which tests failed, what the errors were, and the content of relevant attachments.
What it is NOT
Details
- Repository
- github.com/hubertgajewski/playwright-report-mcp
- Category
- Web & Browser Automation
- Package
playwright-report-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related Web & Browser Automation MCP servers
View all
Web Scraper to Markdown APIbr0ski777/web-scraper-x402Extract clean markdown from any URL. Removes boilerplate. For RAG pipelines. x402.0stars
k11 Playwright QAk11-software-solutions/k11techlab-playwright-qa-mcpUser stories to verified Playwright tests, and self-healing locators with an audit trail.0starsk11 Selenium QAk11-software-solutions/k11techlab-selenium-qa-mcpSelenium tests from user stories (Python or Java) and self-healing locators with an audit trail.0stars
Headless Oraclelembagang/headless-oracle-v5Ed25519-signed market open/close receipts for NYSE, NASDAQ, LSE, JPX, Euronext, HKEX, and SGX.0starsHeadless Oracle Mcplembagang/headless-oracle-v5Ed25519-signed market-state receipts for 28 exchanges. Fail-closed pre-trade gate.0stars
Chromedevtoolsmcp Mcpclauxel/chrome-devtools-session-mcp-mcpA paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,0stars