check_health
AI agents call check_health to retrieve information from PostCrawl MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Health check tools typically query server status or availability without side effects. Given the server's purpose (content access) and the generic nature of 'check_health,' this most likely retrieves diagnostic information about the service. With an empty description, confidence is moderate but the classification leans toward Read as the least harmful category consistent with typical health-check patterns.
From the tool's definition Tool name 'check_health' combined with context of a server that provides search and content extraction capabilities suggests a diagnostic or status-checking function. The empty description limits definitive assessment.
Attacks that exploit this kind of access
check_health. It is categorised as a Read tool in the PostCrawl MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PostCrawl MCP Server MCP server in PolicyLayer and add a rule for check_health: 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 PostCrawl MCP Server. Nothing to install.
check_health 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 check_health 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 check_health. 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.
check_health is provided by the PostCrawl MCP Server MCP server (post-crawl/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →