Check CRDP service liveness
AI agents call check_liveness to retrieve information from Thales Cdsp Crdp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a passive monitoring/diagnostic tool that retrieves service status information. It has no side effects, does not modify data, does not execute arbitrary code, and does not trigger business logic. It fits the 'Read' category as a simple query operation. Severity is low because misuse would only return status information, with minimal blast radius.
From the tool's definition Tool name is 'check_liveness' and description states 'Check CRDP service liveness' — a health/status check operation that queries the service state without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Check CRDP service liveness. It is categorised as a Read tool in the Thales Cdsp Crdp MCP Server, which means it retrieves data without modifying state.
Register the Thales Cdsp Crdp MCP server in PolicyLayer and add a rule for check_liveness: 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 Thales Cdsp Crdp. Nothing to install.
check_liveness 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_liveness 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_liveness. 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_liveness is provided by the Thales Cdsp Crdp MCP server (sanyambassi/thales-cdsp-crdp-mcp-server). 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 →