Compute content-addressed request identity (SHA-256 of agentId + actionType + scope + normalized timestamp). Two receipts with the same action_ref describe the same request.
Part of the Agent Passport System — Cryptographic Identity for AI Agents server.
Free to start. No card required.
AI agents call compute_action_ref to retrieve information from Agent Passport System — Cryptographic Identity for AI Agents without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though compute_action_ref only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"compute_action_ref": {}
}
}See the full Agent Passport System — Cryptographic Identity for AI Agents policy for all 150 tools.
These attack patterns abuse exactly the kind of access compute_action_ref gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Compute content-addressed request identity (SHA-256 of agentId + actionType + scope + normalized timestamp). Two receipts with the same action_ref describe the same request.. It is categorised as a Read tool in the Agent Passport System — Cryptographic Identity for AI Agents MCP Server, which means it retrieves data without modifying state.
Register the Agent Passport System — Cryptographic Identity for AI Agents MCP server in PolicyLayer and add a rule for compute_action_ref: 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 Agent Passport System — Cryptographic Identity for AI Agents. Nothing to install.
compute_action_ref 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 compute_action_ref 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 compute_action_ref. 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.
compute_action_ref is provided by the Agent Passport System — Cryptographic Identity for AI Agents MCP server (agent-passport-system-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 150 Agent Passport System — Cryptographic Identity for AI Agents tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.