AI agents call risk_policy_get to retrieve information from LocalAnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries configuration or policy state without modifying, executing, or affecting system behavior. It is informational only, making it a Read category risk with low severity since disclosure of policy metadata poses minimal direct harm.
From the tool's definition Tool name is 'risk_policy_get' and description states it retrieves/gets 'the current risk policy (mode + whether risk-1 needs approval)'. The verb 'get' and passive retrieval of policy state indicate a read-only query with no side effects.
Attacks that exploit this kind of access
Get the current risk policy (mode + whether risk-1 needs approval). It is categorised as a Read tool in the LocalAnt MCP Server, which means it retrieves data without modifying state.
Register the LocalAnt MCP server in PolicyLayer and add a rule for risk_policy_get: 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 LocalAnt. Nothing to install.
risk_policy_get 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 risk_policy_get 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 risk_policy_get. 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.
risk_policy_get is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →