Provision a complete ENS identity for an AI agent in one call. Describe your agent's purpose and budget — get back recommended available names, a multi-step registration recipe (commit → register → set agent records), and ready-to-sign transaction data. The registration recipe includes agent iden...
Risk signalsHigh parameter count (11 properties)
Part of the Name Whisper — ENS Intelligence Layer server.
Free to start. No card required.
AI agents invoke provision_agent_identity to trigger processes or run actions in Name Whisper — ENS Intelligence Layer. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
provision_agent_identity can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"provision_agent_identity": {
"limits": [
{
"counter": "provision_agent_identity_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Name Whisper — ENS Intelligence Layer policy for all 42 tools.
These attack patterns abuse exactly the kind of access provision_agent_identity gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Provision a complete ENS identity for an AI agent in one call. Describe your agent's purpose and budget — get back recommended available names, a multi-step registration recipe (commit → register → set agent records), and ready-to-sign transaction data. The registration recipe includes agent identity records (ENSIP-25: ai.agent, ai.purpose, ai.capabilities + ENSIP-26: agent-context) as a mandatory final step — these records make the agent discoverable in the ENS Agents directory. ENSIP-25 agent-registration binding is included when an agentRegistry is provided. IMPORTANT: The calling AI MUST execute all steps in the recipe, including the final set_ens_records step. Agent identity is not complete until the text records are on-chain. Example: "DeFi trading bot, 0.05 ETH budget" → names like swiftswap.eth with full registration + identity setup instructions.. It is categorised as a Execute tool in the Name Whisper — ENS Intelligence Layer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Name Whisper — ENS Intelligence Layer MCP server in PolicyLayer and add a rule for provision_agent_identity: 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 Name Whisper — ENS Intelligence Layer. Nothing to install.
provision_agent_identity is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the provision_agent_identity 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 provision_agent_identity. 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.
provision_agent_identity is provided by the Name Whisper — ENS Intelligence Layer MCP server (https://namewhisper.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 42 Name Whisper — ENS Intelligence Layer 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.