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 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| 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
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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