tibet-pol-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tibet-pol-mcp run health check on my_stack"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tibet-pol-mcp
MCP server for tibet-pol — machine & process health monitoring with TIBET provenance.
Run infrastructure integrity checks via JSON templates. Every step is verified, dependency-chained, and signed with TIBET tokens. Like htop meets audit trail.
Part of the TIBET ecosystem by HumoticaOS.
Install
pip install tibet-pol-mcpRelated MCP server: boilerforge
Claude Code / Claude Desktop Config
{
"mcpServers": {
"pol": {
"command": "tibet-pol-mcp",
"env": {
"TIBET_POL_TEMPLATES": "/path/to/your/templates"
}
}
}
}Available Tools
Tool | Description |
| Run health check against a template |
| List available check templates |
| Get template details and steps |
| Compare two runs — track infrastructure drift |
| Generate HTML report from results |
| One-shot health percentage + failed steps |
How It Works
Define infrastructure checks as JSON templates:
{
"process_id": "my_stack",
"name": "My Infrastructure",
"steps": [
{
"id": "api_health",
"name": "API responds",
"check": "curl -sf http://localhost:8000/health",
"critical": true,
"intent": "Core API must be reachable"
},
{
"id": "db_connected",
"name": "Database connection",
"check": "pg_isready -h localhost",
"dependencies": ["api_health"],
"critical": true
}
]
}Then check via MCP:
pol_check("my_stack")
# → 100% health, all steps valid, TIBET token chain
pol_quick_health("my_stack")
# → {"health": "100%", "checksum": "2/2", "failed_steps": []}Step Statuses
Status | Meaning |
| Check passed |
| Was passing, now failing (state change) |
| Check failed |
| Dependency failed, step skipped |
| Not yet checked |
Template Features
Dependencies: Steps can depend on other steps (topological sort)
Critical flags: Critical failures block dependent steps
Remediation:
on_failurecommands for auto-fixIntents: Document WHY each check exists
Success criteria: Min percentage, all-critical rules
Alerts: Commands on critical failure or threshold breach
Environment Variables
Variable | Default | Description |
|
| Templates directory |
Related TIBET Packages
tibet-audit— Core TIBET provenancetibet-pol— CLI/Python API (dependency)tibet-triage-mcp— Process triage MCP servertibet-phantom-mcp— Cross-device AI sessionstibet-ipoll-mcp— AI-to-AI messaging
License
MIT — HumoticaOS
Available Tools
6 toolspol_checkA
Run a process integrity check against a template.
Executes all steps defined in the template, respecting dependency chains and critical flags. Returns structured results with:
Overall health percentage and checksum
Per-step status (valid/broken/blocked/drift)
Duration per step
TIBET token chain for full audit trail
Args: template: Template name or path (e.g., "humotica_full_stack", "p520_machine.json", or full path) output_json: Return raw JSON (default: true)
Returns: Check results with summary, step details, and TIBET provenance
Inputs: template (required), output_json.
pol_diffA
Compare two check runs to see what changed.
Shows checksum changes, status changes, and step-level differences. Useful for tracking infrastructure drift over time.
Args: result_a: Path to first result JSON result_b: Path to second result JSON
Returns: Diff showing what changed between runs
Inputs: result_a (required), result_b (required).
pol_quick_healthA
Quick health summary — just the checksum and status.
Runs a full check but returns only the summary: percentage, checksum (passed/total), status, and any failed steps.
Args: template: Template name (default: humotica_full_stack)
Returns: Quick summary with health percentage and failed step names
Inputs: template.
pol_reportA
Generate an HTML report from check results.
Creates a formatted HTML file with summary, step table, and collapsible TIBET token chain.
Args: result_path: Path to check result JSON output: Output HTML file path (default: auto-generated)
Returns: Path to generated HTML report
Inputs: result_path (required), output.
pol_template_infoC
Get detailed info about a template — all steps, dependencies, and intents.
Args: template: Template name or path
Returns: Full template structure with steps, dependency graph, and success criteria
Inputs: template (required).
pol_templatesA
List available process check templates.
Shows all .json templates in the templates directory with their process ID, name, step count, and critical step count.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: running full checks, quick health summaries, comparing results, generating HTML reports, viewing template details, and listing templates. The only similar pair is pol_check and pol_quick_health, but the latter is explicitly a simplified subset, so no ambiguity.
All tools follow the consistent pattern 'pol_<descriptive_name>', using lowercase with underscores (snake_case). The verbs and nouns are clear and predictable (check, diff, quick_health, report, template_info, templates).
With 6 tools, the count is well-scoped for a process checking server. Each tool serves a distinct function without being redundant or excessive.
The tool surface covers the full workflow: running checks (full and quick), comparing runs, generating reports, and exploring templates. There are no obvious missing operations for the server's stated purpose of process integrity verification.
Maintenance
Related MCP Connectors
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
MCP Spec Compliance MCP — audits any MCP server.json against the official Model Context Protocol
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for tibet-triage — process triage, flare rescue & reproducibility bundles with TIBET provenance.MIT
- AlicenseAqualityDmaintenanceArchitecture governance MCP server for AI-built codebases, enabling health checks, template management, and project scaffolding with migration support.54 npmMIT
- AlicenseAqualityDmaintenanceAn MCP server for auditing automation health, finding failures, stale logs, and non-functional endpoints that report success while quietly failing.7MIT
- AlicenseAqualityFmaintenanceMCP server for monitoring health of MCP servers, GitHub Actions, GitLab pipelines, and HTTP endpoints with health history, TLS expiry, assertions, diagnostics, and alerts.22111 npm2MIT