Flakiness Knowledge Graph Mcp
A Playwright reporter and MCP server that accumulates test run history into SQLite and exposes it through eight analysis tools. You get flakiness rankings by test and browser combination, exact commit SHAs where tests went from stable to flaky (using GITHUB_SHA and similar CI variables), semantic error clustering that normalizes UUIDs and dynamic values with Levenshtein matching, and trend analysis over arbitrary day ranges. The reporter writes every test result to the database automatically. Useful when you need to distinguish historical flakes from new regressions in CI, or when you want an AI agent to answer whether a failing test has been unreliable for weeks. Pairs well with playwright-trace-decoder-mcp for combining "what failed this time" with "has this always been flaky."
- tools
- 8
- transport
- STDIO
- last updated
- May 19, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
get_flaky_testsTests ranked by flakiness rate (failed+flaky / total runs)
Tests ranked by flakiness rate (failed+flaky / total runs)
No parameter schema in public metadata yet.
get_test_historyFull run history for a specific test — status, duration, error, retry, browser, OS
Full run history for a specific test — status, duration, error, retry, browser, OS
No parameter schema in public metadata yet.
get_failure_patternsFailure rates broken down by browser × OS combination
Failure rates broken down by browser × OS combination
No parameter schema in public metadata yet.
get_slow_testsTests ranked by average duration
Tests ranked by average duration
No parameter schema in public metadata yet.
get_error_groupsFailures clustered by exact error prefix — surfaces shared root causes across tests
Failures clustered by exact error prefix — surfaces shared root causes across tests
No parameter schema in public metadata yet.
get_flakiness_trendDaily flakiness rate over the last N days — shows whether a test is getting worse
Daily flakiness rate over the last N days — shows whether a test is getting worse
No parameter schema in public metadata yet.
cluster_semantic_error_treesLike get_error_groups but normalises dynamic values (UUIDs, IDs, URLs) first, then fuzzy-merges with Levenshtein
Like get_error_groups but normalises dynamic values (UUIDs, IDs, URLs) first, then fuzzy-merges with Levenshtein
No parameter schema in public metadata yet.
correlate_git_commit_flakinessFinds the exact commit SHA where a test transitioned stable→flaky (or back), with branch and author
Finds the exact commit SHA where a test transitioned stable→flaky (or back), with branch and author
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
📊 flakiness-knowledge-graph-mcp
A Playwright custom reporter + MCP server that builds a local flakiness knowledge graph from your test run history. Ask your AI agent which tests are unreliable, on which browser, and whether they're getting worse.
🤔 The Problem
A single Playwright trace tells you what failed right now. It doesn't tell you whether this test has been silently flaking for two weeks, or only fails on Firefox in CI, or is getting slower with every release.
This tool fixes that by accumulating run history into a SQLite database and exposing it to AI agents via MCP.
🛠️ Tools
Details
- Repository
- github.com/vola-trebla/flakiness-knowledge-graph-mcp
- Categories
- Web & Browser Automation, AI & LLM Tools, Documents & Knowledge
- Package
flakiness-knowledge-graph-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from vola-trebla
- 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
- Playwright Trace Decoder Mcp1
- Ast Impact Mapper Mcp
- Env Secret Exposure Analyzer Mcp
Related Web & Browser Automation MCP servers
View all
Next AI Draw.iodayuanjiang/next-ai-draw-iodraw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand36.9Kstars
Spree Commerce developer docs for AI agentsspree/spreeSpree Commerce docs for AI coding agents: build headless B2B and marketplace ecommerce on its APIs.15.8Kstars
Actionbookactionbook/actionbookLet your AI agent operate any website through a real, logged-in browser session.1.6Kstars
Unbrowseunbrowse-ai/unbrowseWebsites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.904stars
FableCutronak-create/fablecutZero-dependency browser video editor AI agents drive via a JSON timeline over MCP; ffmpeg export.780stars
DrissionPage MCPjumodada/drissionpage-mcp-serverLocal browser automation for MCP clients powered by DrissionPage.480stars