Menu
Monitor Railway projects, diagnose deployment failures, and audit infrastructure using read-only MCP tools
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.
Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.
Production-grade PR review with execution-verified suggestions. Reads repository conventions, history, and security surfaces before reviewing. For every suggested fix, attempts to compile and test it in the sandbox — the comment includes proof. Modelled on GitHub Copilot's agentic architecture with one critical advantage: the sandbox is already running.
Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.
Open and manage GitHub pull requests through Kai MCP tools — propose changes, monitor CI, iterate on failures, and merge. No git tokens are shared to the sandbox; every GitHub operation goes through the backend via the workspace's GitHub App installation.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
| name | railway-monitor |
| description | Monitor Railway projects, diagnose deployment failures, and audit infrastructure using read-only MCP tools |
| version | 1.0.0 |
| author | kai-agent |
| metadata | {"kai":{"tags":["kai","railway","monitoring","deployments","infrastructure"],"related_skills":["aws-performance","aws-cost-optimizer"]}} |
Monitor, diagnose, and audit Railway infrastructure. All operations are read-only — no deploys, restarts, or config changes.
RAILWAY_API_TOKEN set in kai-backend envmcp__kai__railway_*Get a full picture of what's running.
List all projects:
railway_list_projects(workspaceId)
For each project, get details:
railway_project_detail(workspaceId, projectId="...")
Returns: services, environments, volumes
Present as:
| Project | Services | Environments | Volumes |
|---|
Check if everything is running correctly.
Quick health overview (best starting point):
railway_project_health(workspaceId, projectId="...")
Returns every service × environment with latest deployment status.
Or per-environment:
railway_deployment_status(workspaceId, projectId="...", environmentId="...")
Shows all services in that environment.
Flag issues:
FAILED or CRASHED → immediate attentionBUILDING for >10 minutes → possibly stuckWhen a service is down, follow this sequence:
Check latest deployment:
railway_latest_deployment(workspaceId, projectId, environmentId, serviceId)
Note the status and deploymentId.
If build failed — read build logs:
railway_build_logs(workspaceId, deploymentId="...", limit=200)
Look for: dependency install errors, compile errors, Dockerfile issues.
If build succeeded but runtime crashed — read runtime logs:
railway_deployment_logs(workspaceId, deploymentId="...", limit=200)
Look for: uncaught exceptions, OOM kills, port binding failures, missing env vars.
Check HTTP errors:
railway_http_logs(workspaceId, deploymentId="...", limit=100)
Look for: 5xx status codes, high response times (>5s), patterns in failing paths.
Check environment variables:
railway_list_variables(workspaceId, projectId, environmentId, serviceId)
Verify expected vars exist (DATABASE_URL, REDIS_URL, API_KEY, etc.).
Check variable references:
railway_variable_references(workspaceId, projectId, environmentId, serviceId)
Verify ${{...}} references resolve to actual services.
List all domains:
railway_list_domains(workspaceId, projectId, environmentId, serviceId)
Check for issues:
certificateStatus != "VALID" → SSL cert problemstatus != "OK" → DNS not configuredList volumes:
railway_list_volumes(workspaceId, projectId)
Check each volume:
railway_volume_detail(workspaceId, volumeInstanceId="...")
state != "READY"currentSizeMB approaching storage limitVerify backups exist:
railway_volume_backups(workspaceId, volumeInstanceId="...")
Verify all services have the expected environment variables.
For each service in the production environment:
railway_list_variables(workspaceId, projectId, environmentId, serviceId)
Common expected variables:
PORT, NODE_ENV, DATABASE_URLAPI_KEY, JWT_SECRET, CORS_ORIGINREDIS_URL, QUEUE_NAMELOG_LEVELCheck references make sense:
railway_variable_references(workspaceId, projectId, environmentId, serviceId)
${{Postgres.DATABASE_URL}} style refs point to real servicesUseful for understanding recent changes.
railway_list_deployments(workspaceId, projectId, environmentId, serviceId, limit=20)
FAILED → SUCCESS → FAILED patterns = flaky deploysProject: {name} Status: Healthy / Warning / Critical
| Service | Environment | Deploy Status | Last Deploy | Issue |
|---|---|---|---|---|
| api | production | SUCCESS | 2h ago | - |
| worker | production | CRASHED | 30m ago | OOM in logs |
| web | staging | BUILDING | 15m ago | Possibly stuck |
Issues Found:
Variable Audit:
REDIS_URL on worker service${{OldDb.URL}} (service deleted)Recommendations: