Playwright Trace Decoder Mcp
When Playwright tests fail in CI, you get a trace.zip that's too large for LLM context windows and full of binary data agents can't parse. This server unpacks those archives into 16 focused tools that expose exactly what you need for root cause analysis. You can map locators to source code lines, extract ARIA trees as compressed YAML, filter network logs to only 4xx/5xx responses, correlate DOM mutations with in-flight requests, and pull screenshots from the moment of failure. It handles both local paths and HTTPS URLs, supports pagination to control token costs, and includes a trim operation that strips non-critical screenshots to shrink archives by 70-80%. Reach for this when you're tired of manually copying Playwright logs into ChatGPT and want an agent to diagnose flaky selectors, race conditions, and timing issues automatically.
- GitHub stars
- 1
- tools
- 19
- transport
- STDIO
- last updated
- May 19, 2026
Tools
19 toolsPublic tool metadata for what this MCP can expose to an agent.
get_test_metadataBrowser, platform, viewport, test title, wall-clock start time
Browser, platform, viewport, test title, wall-clock start time
No parameter schema in public metadata yet.
get_trace_summaryFailing action + top-level error + total action count
Failing action + top-level error + total action count
No parameter schema in public metadata yet.
get_action_timelinePaginated list of all actions with API names, locators, and timings
Paginated list of all actions with API names, locators, and timings
No parameter schema in public metadata yet.
get_filtered_network_logsOnly 4xx/5xx responses — static assets (CSS, JS, fonts, images) stripped
Only 4xx/5xx responses — static assets (CSS, JS, fonts, images) stripped
No parameter schema in public metadata yet.
get_console_errorsJS exceptions and warnings from the browser console
JS exceptions and warnings from the browser console
No parameter schema in public metadata yet.
get_element_state_at_failureFailing locator, error message, and raw before/after metadata
Failing locator, error message, and raw before/after metadata
No parameter schema in public metadata yet.
extract_trace_metadata_strictFormat version, retry session breakdown, HAR payload mode (embed/attach/omit)
Format version, retry session breakdown, HAR payload mode (embed/attach/omit)
No parameter schema in public metadata yet.
get_aria_accessibility_treeARIA accessibility tree as compact YAML (~90% fewer tokens than raw HTML). Defaults to the snapshot at the failed action.
ARIA accessibility tree as compact YAML (~90% fewer tokens than raw HTML). Defaults to the snapshot at the failed action.
No parameter schema in public metadata yet.
get_dom_mutation_deltaSet-diff of ARIA lines before vs after a specific action — added/removed elements only, not two full DOM dumps
Set-diff of ARIA lines before vs after a specific action — added/removed elements only, not two full DOM dumps
No parameter schema in public metadata yet.
get_screenshot_at_failureBase64 JPEG screenshot closest to the moment of failure. Use when ARIA tree is empty (captcha, blank page).
Base64 JPEG screenshot closest to the moment of failure. Use when ARIA tree is empty (captcha, blank page).
No parameter schema in public metadata yet.
analyze_race_conditionsNetwork requests that were in-flight when an interaction or assertion fired
Network requests that were in-flight when an interaction or assertion fired
No parameter schema in public metadata yet.
correlate_dom_and_networkFor each action where a fetch completed and the DOM mutated within ±100ms: triggering URL, response status, body snippet, and exact nodes added/removed
For each action where a fetch completed and the DOM mutated within ±100ms: triggering URL, response status, body snippet, and exact nodes added/removed
No parameter schema in public metadata yet.
extract_critical_framesExtracts key screencast screenshots (base64) from a temporal window around failure, resolved with step titles
Extracts key screencast screenshots (base64) from a temporal window around failure, resolved with step titles
No parameter schema in public metadata yet.
get_causal_chain_for_failureChronological chain of preceding actions, network errors, and console errors leading to the failure (default window: 5 s)
Chronological chain of preceding actions, network errors, and console errors leading to the failure (default window: 5 s)
No parameter schema in public metadata yet.
generate_error_signatureStable 12-char SHA-1 hash of the normalized error — use to group duplicate failures across parallel CI runs
Stable 12-char SHA-1 hash of the normalized error — use to group duplicate failures across parallel CI runs
No parameter schema in public metadata yet.
compare_tracesLCS-aligned action sequence between a passing and failing run: structural divergence, timing anomalies (>500 ms), unmatched actions, network delta
LCS-aligned action sequence between a passing and failing run: structural divergence, timing anomalies (>500 ms), unmatched actions, network delta
No parameter schema in public metadata yet.
map_locator_to_sourceMaps a failing browser interaction (or specific action index) to the exact line of test code via runner execution stack
Maps a failing browser interaction (or specific action index) to the exact line of test code via runner execution stack
No parameter schema in public metadata yet.
detect_performance_anomaliesRanked list of slow actions and frame drops with suspected_cause (main thread blocked / network saturation / navigation timeout). Also reports p50/p95 action duration and a memory leak flag.
Ranked list of slow actions and frame drops with suspected_cause (main thread blocked / network saturation / navigation timeout). Also reports p50/p95 action duration and a memory leak flag.
No parameter schema in public metadata yet.
trim_trace_archiveShrinks trace zip by deleting screenshots outside critical failure window (t_fail - 5s to t_fail + 1s). Returns trimmed path & size delta.
Shrinks trace zip by deleting screenshots outside critical failure window (t_fail - 5s to t_fail + 1s). Returns trimmed path & size delta.
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 languageReadme
🎭 playwright-trace-decoder-mcp
An MCP server that unpacks and structures Playwright trace.zip archives so AI agents can perform root-cause analysis on CI failures — without drowning in raw JSON or blowing up the context window.
🤔 The Problem
When a Playwright test fails in CI, you get a trace.zip. It's a binary blob. LLMs can't read it natively, and dumping the raw contents exceeds the context window. Engineers end up copying log snippets into ChatGPT manually like it's 2022.
Details
- Repository
- github.com/vola-trebla/playwright-trace-decoder-mcp
- Categories
- Web & Browser Automation, Monitoring & Observability
- Package
playwright-trace-decoder-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from vola-trebla
- Ast Impact Mapper Mcp
- Env Secret Exposure Analyzer Mcp
- Flakiness Knowledge Graph Mcp
- Ndjson Local Log Triage Mcp
- Playwright Network Chaos Mcp
- Playwright Spatial Layout Mcp
- Sourcemap Retrace Mcp
- Tailwind Context Resolver Mcp
- Tsconfig Inheritance Flattener Mcp
- V8 Cpu Profile Decoder Mcp
- Release Readiness Triage Mcp
- React Render Profile Mcp2
Related Web & Browser Automation MCP servers
View all
WordPress Headlessaj-ua/wp-headless-mcpRead WordPress content, ACF fields, and Yoast SEO data, and safely edit drafts.0stars
Apex Flow 3D Scraperapexflowlabsllc/apex-flow-web-scraperScrape, crawl and monitor public pages as Markdown with change tracking and source receipts.0stars
Playwright Report Mcphubertgajewski/playwright-report-mcpRun Playwright tests and surface structured results for AI agents doing test failure analysis.0stars
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