AI agents call get-health-check-groups to retrieve information from Mcp Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system monitoring information without creating, modifying, deleting, or executing any operations. It is a passive read of existing health check group data, making it a standard Read category tool with low severity since it only exposes monitoring metadata.
From the tool's definition Tool description states 'Gets a paged list of health check groups' - a retrieval operation with no modification or side effects. The verb 'Gets' and the read-only nature of querying system health check metadata confirm this is a data retrieval operation.
Attacks that exploit this kind of access
Gets a paged list of health check groups for system monitoring. It is categorised as a Read tool in the Mcp Dev MCP Server, which means it retrieves data without modifying state.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for get-health-check-groups: 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 Mcp Dev. Nothing to install.
get-health-check-groups 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 get-health-check-groups 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 get-health-check-groups. 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.
get-health-check-groups is provided by the Mcp Dev MCP server (@umbraco-cms/mcp-dev). 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 →