run the content policy on a brief before ordering. Free.
AI agents call validate_brief to retrieve information from Token of Esteem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
validate_brief performs a pre-submission verification check—a read-only operation that retrieves or applies validation rules to assess conformance. It has no side effects: it does not create, modify, delete, or execute anything. The tool exists to prevent misuse downstream (e.g., before create_gift is called), but the tool itself only reads and reports.
From the tool's definition Tool validates content against policy ('run the content policy on a brief') without modifying data, placing orders, or executing external operations. It is a checking/querying function that returns policy compliance status.
Attacks that exploit this kind of access
run the content policy on a brief before ordering. Free. It is categorised as a Read tool in the Token of Esteem MCP Server, which means it retrieves data without modifying state.
Register the Token of Esteem MCP server in PolicyLayer and add a rule for validate_brief: 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 Token of Esteem. Nothing to install.
validate_brief 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 validate_brief 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 validate_brief. 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.
validate_brief is provided by the Token of Esteem MCP server (tokenofesteem/mcp). 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 →