By konflux-ci
DevLake engineering metrics skills — query data, generate reports, and scaffold automated report repos using the Konflux DevLake MCP server
This skill should be used whenever the user asks about engineering metrics, software delivery performance, or team productivity data — including PR statistics, DORA metrics (deployment frequency, lead time, change failure rate, recovery time), code coverage, CI/CD health, build success rates, flaky or failing tests, retest patterns, PR cycle time (coding time, pickup time, review time), merge throughput, incidents, or Jira feature tracking. Use this skill even when the user doesn't mention "DevLake" explicitly — any question about "how many PRs", "what's our deploy rate", "which tests are flaky", "compare team metrics", "coverage trends", "build failures", or "change failure rate" should trigger this skill. Also trigger for cross-team comparisons, historical trend analysis, bottleneck identification, and any request to query or analyze engineering data from repositories.
Trigger when the user wants a formatted HTML report file — DORA metrics report, PR cycle time report, engineering excellence report, coverage report, or retest analysis report. Not for quick questions (use devlake skill instead).
Trigger when the user wants to create a new GitLab repo for automated, scheduled engineering reports — setting up CI pipelines, DSPy prompts, and GitLab Pages publishing from DevLake data.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A MCP server that enables natural language querying of Konflux DevLake databases. This server acts as a bridge between AI assistants and your DevLake database, allowing you to ask questions in plain language and get structured data back.
pip install -r requirements.txt
python konflux-devlake-mcp.py --transport http --host 0.0.0.0 --port 3000 --db-host localhost --db-port 3306 --db-user root --db-password password --db-database lake
docker build -t konflux-devlake-mcp:latest .
docker run -d \
--name konflux-mcp-server \
-p 3000:3000 \
-e DB_HOST=your_db_host \
-e DB_PORT=3306 \
-e DB_USER=root \
-e DB_PASSWORD=your_password \
-e DB_DATABASE=lake \
-e LOG_LEVEL=INFO \
konflux-devlake-mcp:latest
docker tag konflux-devlake-mcp:latest quay.io/flacatus/mcp-lake:1.0.0
docker push quay.io/flacatus/mcp-lake:1.0.0
| Argument | Description | Example |
|---|---|---|
--transport | Transport protocol (stdio/http) | --transport http |
--host | Server host | --host 0.0.0.0 |
--port | Server port | --port 3000 |
--db-host | Database host | --db-host localhost |
--db-port | Database port | --db-port 3306 |
--db-user | Database username | --db-user root |
--db-password | Database password | --db-password your_password |
--db-database | Database name | --db-database lake |
--log-level | Logging level | --log-level INFO |
The server includes configurable timeout settings optimized for LLM connections:
| Environment Variable | Description | Default |
|---|---|---|
SERVER_TIMEOUT_KEEP_ALIVE | HTTP keep-alive timeout in seconds | 600 (10 minutes) |
SERVER_TIMEOUT_GRACEFUL_SHUTDOWN | Graceful shutdown timeout in seconds | 120 (2 minutes) |
DB_CONNECT_TIMEOUT | Database connection timeout in seconds | 60 (1 minute) |
DB_READ_TIMEOUT | Database read timeout in seconds | 600 (10 minutes) |
DB_WRITE_TIMEOUT | Database write timeout in seconds | 120 (2 minutes) |
These high default values ensure that long-running LLM requests and complex database queries don't timeout prematurely.
The server supports OIDC authentication for securing MCP endpoints. When enabled, all requests to /mcp endpoints require a valid token.
| Environment Variable | Description | Default |
|---|---|---|
OIDC_ENABLED | Enable OIDC authentication | false |
OIDC_ISSUER_URL | OIDC issuer URL (e.g., https://sso.redhat.com/auth/realms/redhat-external) | - |
OIDC_CLIENT_ID | OIDC client ID / audience | - |
OIDC_REQUIRED_SCOPES | Comma-separated list of required scopes | - |
OIDC_JWKS_CACHE_TTL | JWKS cache TTL in seconds | 3600 |
OIDC_SKIP_PATHS | Comma-separated paths to skip auth | /health,/security |
OIDC_VERIFY_SSL | Verify SSL certificates | true |
OIDC_OFFLINE_TOKEN_ENABLED | Accept offline tokens (server exchanges for access token) | false |
OIDC_TOKEN_EXCHANGE_CLIENT_ID | Client ID for token exchange (defaults to OIDC_CLIENT_ID) | - |
OIDC_ACCESS_TOKEN_CACHE_BUFFER | Seconds before expiry to refresh access token | 60 |
Example: Enable Red Hat SSO authentication with access tokens
export OIDC_ENABLED=true
export OIDC_ISSUER_URL="https://sso.redhat.com/auth/realms/redhat-external"
export OIDC_CLIENT_ID="cloud-services"
Example: Enable offline token mode (server handles token exchange)
Claude skills and utilities for Konflux CI/CD integration and workflow automation.
A plugin to analyze and trigger Konflux builds
Use when investigating Konflux Tekton pipeline failures, PipelineRun/TaskRun issues, build failures, or CI/CD workflow problems. Provides systematic debugging methodology using standard kubectl commands for comprehensive root cause analysis in Konflux environments.
Quick reference for Konflux CI/CD Custom Resources (RP, RPA, ITS) - helps users understand Applications, Components, Snapshots, IntegrationTestScenarios, ReleasePlans, namespace placement, common abbreviations, and confusions
Use when tracing Konflux builds from image references, finding build logs from artifacts, or verifying source commits for container images - extracts provenance attestations to navigate from images back to builds and source code
npx claudepluginhub konflux-ci/konflux-devlake-mcpGenerate analytics reports and dashboard configurations from project data
Review TypeScript and JavaScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull requests or diffs containing TypeScript/JavaScript code.
DevOps automation: ClickHouse, Doppler, MLflow, Cloudflare Workers, pueue orchestration, notifications, session recovery, MiniMax consensus analysis
Productivity metrics and analytics dashboard
Centralized Claude Code configuration: Docker-first guards, permissions, MCP gateway, and workflow skills
Comprehensive data engineering toolkit combining ETL pipelines, data quality, and data architecture. Includes data architect agent for holistic data engineering decisions.