get_client_health
AI agents call get_client_health to retrieve information from CMR Client Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents health metrics about client accounts. No description is provided for the specific tool, but the server's stated purpose is to provide 'reads' (observations) on account health without any mentioned capability to modify data. The 'get_' prefix and context indicate a read-only query operation with no side effects.
From the tool's definition Tool name 'get_client_health' indicates a retrieval operation. Server description explicitly states the tool enables teams to 'get instant, natural-language health reads on client accounts' with no modification capabilities mentioned.
Attacks that exploit this kind of access
get_client_health. It is categorised as a Read tool in the CMR Client Health MCP Server, which means it retrieves data without modifying state.
Register the CMR Client Health MCP server in PolicyLayer and add a rule for get_client_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 CMR Client Health. Nothing to install.
get_client_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 get_client_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 get_client_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.
get_client_health is provided by the CMR Client Health MCP server (rahulmodugula/cmr-client-health-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 →