get_api_reference
AI agents call get_api_reference to retrieve information from Thales Cdsp Csm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests a read-only operation to retrieve API reference documentation. Without a description, confidence is moderated, but the naming pattern is consistent with informational retrieval rather than data manipulation or execution. Given the context of a secrets management server, this is likely a safe documentation lookup.
From the tool's definition Tool name 'get_api_reference' indicates retrieval of API documentation or reference material. No description provided.
Attacks that exploit this kind of access
get_api_reference. It is categorised as a Read tool in the Thales Cdsp Csm MCP Server, which means it retrieves data without modifying state.
Register the Thales Cdsp Csm MCP server in PolicyLayer and add a rule for get_api_reference: 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 Csm. Nothing to install.
get_api_reference 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_api_reference 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_api_reference. 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_api_reference is provided by the Thales Cdsp Csm MCP server (sanyambassi/thales-cdsp-csm-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 →