Skip to main content
Glama
gurevich89

allure-mcp-analyzer

by gurevich89
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

šŸ” Allure MCP Analyzer ā€” AI-driven root-cause analysis for test failures

An MCP server + CLI that reads Allure results, clusters failures by normalized error signature (deterministic, no LLM), and then asks an LLM to explain each cluster ā€” product bug, test bug, infrastructure, flaky, or data.

This is the pattern I use to turn a 300-red-test CI run into "3 root causes, here is what to do" in seconds. The clustering step is what makes it cheap and reliable: the LLM analyzes a handful of clusters, not every test.

CI

āœØ What's inside

Area

Highlights

Parsing

Reads allure-results/*-result.json (status, message, trace, labels, timings)

Clustering

Normalizes volatile tokens (ids, hex, timestamps, paths, numbers) ā†’ stable signature ā†’ clusters sorted by impact

Root-cause analysis

One LLM call per cluster; strict JSON contract (category, summary, confidence, evidence, suggested_action) with defensive parsing

Pluggable LLM

FakeLLM (offline, deterministic ā€” used in tests & CI without a key) or AnthropicLLM (lazy import)

MCP server

Tools: load_results, list_failures, cluster_failures, analyze_cluster, analyze_run

CLI

allure-analyze ./allure-results --md report.md --json report.json --top 5 ā€” exit code 1 when failures exist

Reports

Markdown (PR comment / Slack) with a summary table + collapsible affected-tests lists; JSON for dashboards

Agent Skills

.claude/skills/allure-triage ā€” a Claude Code playbook that runs the whole triage flow

CI

Lint + tests on 3.11/3.12, demo report uploaded as an artifact

Related MCP server: Regression-JIRA Integration System

šŸ“ Layout

src/allure_mcp_analyzer/
ā”œā”€ā”€ parser.py     # Allure results ā†’ TestResult
ā”œā”€ā”€ cluster.py    # signature normalization + clustering
ā”œā”€ā”€ rca.py        # prompt, LLM call, JSON contract ā†’ RootCause
ā”œā”€ā”€ report.py     # Markdown / JSON rendering
ā”œā”€ā”€ llm.py        # LLM protocol, FakeLLM, AnthropicLLM
ā”œā”€ā”€ server.py     # FastMCP server (5 tools)
ā””ā”€ā”€ cli.py
examples/allure-results/   # 9 sample results ā†’ 3 clusters (assertion, timeout, locator)
tests/                     # unittest / pytest
.claude/skills/            # agent skill for CI triage
.mcp.json                  # register the server with Claude Code / Cursor

šŸš€ Quick start

pip install -e ".[dev]"            # core + tests
pytest -q                          # 17 tests, all offline

# CLI on the bundled example (FakeLLM when no API key is set)
allure-analyze examples/allure-results --top 3

Real analysis:

pip install -e ".[llm,mcp]"
export ANTHROPIC_API_KEY=...        # see .env.example
export ANTHROPIC_MODEL=...          # https://docs.claude.com/en/docs/about-claude/models
allure-analyze ./allure-results --md report.md

šŸ¤– As an MCP server (Claude Code / Cursor)

.mcp.json is already in the repo ā€” from the repo root:

claude
> Use allure-analyzer to triage ./allure-results and tell me which clusters block the release.

Or invoke the bundled skill directly: /allure-triage.

šŸ§  How clustering works

"AssertionError: expected total 59.98 but got 49.99"
"AssertionError: expected total 120.00 but got 100.00"
        ā†“ normalize()
"AssertionError: expected total <n> but got <n>"     ā†’ one cluster, 3 tests

Timeouts on a shared dependency collapse the same way, so an outage shows up as one infrastructure cluster instead of fifty unrelated reds.

šŸ”Œ CI integration

The workflow uploads report.md / report.json as an artifact on every run. To post the Markdown as a PR comment, pipe it through gh pr comment --body-file report.md.

šŸ“„ License

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers