openclaw-health-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENCLAW_HEALTH_BACKEND | No | Backend to use for health checks: mock, linux-proc, or openclaw | mock |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| health_overviewA | Full deployment health snapshot — gateway + resources + skill registry + upgrade status + cron + disk in one call. Returns overall HealthLevel (healthy/degraded/critical/unknown) plus per-component breakdown plus ranked critical_findings list. Use this first for a single-pane summary. |
| gateway_statusA | Status of the OpenClaw gateway process: alive/dead, uptime, recent restarts (intentional vs crashes), bind address, PID. Flags 0.0.0.0 binding (default-publicly-exposed config). |
| cpu_memory_healthA | CPU% + memory% + swap% snapshot, kernel OOM-kill count over 24h, load averages. Each component gets a HealthLevel; CRITICAL when OOM-imminent or already triggered. |
| recent_errorsA | Recent error/warning log entries from gateway + skills + cron. Filterable by lookback window and minimum severity. |
| skill_registry_checkA | ClawHub / skill-registry integrity: total skills, recently added/modified, skills with external HTTP endpoints, light heuristic flags. For deep static analysis (prompt-injection patterns, exfiltration), install openclaw-skill-vetter-mcp. |
| last_upgrade_statusA | Last OpenClaw upgrade attempt: from-version, to-version, outcome (success/rollback/failure/in_progress), regression markers detected post-upgrade (e.g., websocket_stalls, cpu_spike). Includes available-upstream-version. |
| cron_healthA | Basic cron summary: total jobs, overdue count, 24h success rate. For richer detection (silent failures, output anomalies, duration drift), install silentwatch-mcp alongside this server. When silentwatch_available=True, the caller should query that server too. |
| disk_usageA | Root-disk usage% + log-directory size + 24h growth + largest log files. Flags >85% as DEGRADED, >95% as CRITICAL. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| diagnose-degraded-health | Walk a HealthSnapshot and propose ranked corrective actions |
| summarize-health-trend | Daily digest of deployment health activity |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Health overview snapshot | Full deployment health snapshot (overall + per-component + critical findings) |
| Gateway status | Current gateway process status |
| CPU + memory metrics | Current CPU/memory/swap snapshot |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/temurkhan13/openclaw-health-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server