Evaluate the currently loaded JamJet policy against a candidate MCP tool name. Returns the matched rule, the decision (allow / block / require_approval / audit), and the matched glob pattern. Use this to dry-run a tool call before issuing it, or to explain why a previous call was blocked. Read-on...
AI agents call policy_evaluate to retrieve information from Jamjet Policy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only evaluates a policy against a candidate tool name and returns a decision. It performs no writes, executions, or modifications of any kind. It is explicitly described as read-only with no side effects, making it a pure query/inspection tool with minimal blast radius.
From the tool's definition Read-only and side-effect free — does not write to the audit log. Returns the matched rule, the decision (allow / block / require_approval / audit), and the matched glob pattern.
Attacks that exploit this kind of access
Evaluate the currently loaded JamJet policy against a candidate MCP tool name. Returns the matched rule, the decision (allow / block / require_approval / audit), and the matched glob pattern. Use this to dry-run a tool call before issuing it, or to explain why a previous call was blocked. Read-only and side-effect free — does not write to the audit log. It is categorised as a Read tool in the Jamjet Policy MCP Server, which means it retrieves data without modifying state.
Register the Jamjet Policy MCP server in PolicyLayer and add a rule for policy_evaluate: 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 Jamjet Policy. Nothing to install.
policy_evaluate 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 policy_evaluate 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 policy_evaluate. 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.
policy_evaluate is provided by the Jamjet Policy MCP server (jamjet-labs/jamjet-policy). 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 →