Get a single CNAC authz policy by ID.
AI agents call get_authz_policy to retrieve information from API-Central without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves an existing authorization policy configuration by its identifier. It performs a read-only query operation with no side effects, state changes, or code execution. The blast radius of misuse is minimal—an adversary would gain visibility into policy settings but cannot alter network configuration, execute commands, or cause data loss.
From the tool's definition Tool name 'get_authz' and description 'Get a single CNAC authz policy by ID' indicate a retrieval operation. The verb 'Get' and singular noun phrase establish this as a data query with no modification or execution.
Attacks that exploit this kind of access
Get a single CNAC authz policy by ID. It is categorised as a Read tool in the API-Central MCP Server, which means it retrieves data without modifying state.
Register the API-Central MCP server in PolicyLayer and add a rule for get_authz_policy: 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 API-Central. Nothing to install.
get_authz_policy 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_authz_policy 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_authz_policy. 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_authz_policy is provided by the API-Central MCP server (secure-ssid/centralmcp). 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 →