Kör en health check för att testa API-anslutningar och systemstatus. ANVÄNDNINGSFALL: - Diagnosticera anslutningsproblem - Verifiera att alla API:er är tillgängliga - Mäta response-tider - Få rekommendationer för förbättringar RETURNERAR: - Overall status (healthy/degraded/unhealthy) - Status för...
AI agents call health_check to retrieve information from Skolverket MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a diagnostic/monitoring tool that queries system health and API status without making any changes. It retrieves metrics and status information, making it a Read operation. Severity is low because misuse would only expose diagnostic data and system metrics, with no capability to modify, delete, execute code, or cause financial impact.
From the tool's definition Tool description states it 'Kör en health check' (runs a health check) to 'testa API-anslutningar och systemstatus' (test API connections and system status).
Documented attack patterns abuse exactly the kind of access health_check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Skolverket MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for health_check:
{
"version": "1",
"default": "deny",
"tools": {
"health_check": {}
}
}health_check is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Kör en health check för att testa API-anslutningar och systemstatus. ANVÄNDNINGSFALL: - Diagnosticera anslutningsproblem - Verifiera att alla API:er är tillgängliga - Mäta response-tider - Få rekommendationer för förbättringar RETURNERAR: - Overall status (healthy/degraded/unhealthy) - Status för varje API (Syllabus, School Units, Planned Education) - Latency för varje API - Konfigurationsinformation - Rekommendationer vid problem EXEMPEL: Kör health_check(includeApiTests=true) för att testa alla API:er. It is categorised as a Read tool in the Skolverket MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Skolverket MCP Server MCP server in PolicyLayer and add a rule for health_check: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Skolverket MCP Server. Nothing to install.
health_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the health_check rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for health_check. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
health_check is provided by the Skolverket MCP Server MCP server (isakskogstad/skolverket-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Skolverket MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
89 Skolverket MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.