High Risk →

sweep

Floor-sweep: buy the CHEAPEST N listed ENS names in a category/collection (or matching a filter) in ONE Seaport transaction. Use this when the user wants "the cheapest N", "sweep the floor", or "buy up to X ETH of" a cohort — rather than naming specific names (that's batch_purchase). Pick the coh...

Part of the Name Whisper — ENS Intelligence Layer server.

sweep can trigger actions in Name Whisper — ENS Intelligence Layer, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE NAME WHISPER — ENS INTELLIGENCE LAYER →

Free to start. No card required.

AI agents invoke sweep 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.

sweep 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.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "sweep": {
      "limits": [
        {
          "counter": "sweep_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Name Whisper — ENS Intelligence Layer policy for all 42 tools.

Get this rule live on your own Name Whisper — ENS Intelligence Layer server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY NAME WHISPER — ENS INTELLIGENCE LAYER →

View all 42 tools →

These attack patterns abuse exactly the kind of access sweep gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so sweep only ever does what you allow.

SECURE NAME WHISPER — ENS INTELLIGENCE LAYER →

Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the sweep tool do? +

Floor-sweep: buy the CHEAPEST N listed ENS names in a category/collection (or matching a filter) in ONE Seaport transaction. Use this when the user wants "the cheapest N", "sweep the floor", or "buy up to X ETH of" a cohort — rather than naming specific names (that's batch_purchase). Pick the cohort with 'category' (a collection slug like "999-club") and/or 'q'/'charType'/'minLength'/'maxLength'. Bound the sweep with 'count' (how many) and/or 'maxBudgetEth' (total spend), plus an optional 'maxPriceEth' per-name cap. It selects cheapest-first across NameWhisper, OpenSea, and Grails, then packs them into one fulfillAvailableAdvancedOrders call (capped at 20 names — run again to continue). NFTs are delivered directly to the buyer; Seaport skips any order that sold since discovery and refunds the excess. The response reports what was swept (with marketplace + price), the total, and how many matched but fell outside the bound.. 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.

How do I enforce a policy on sweep? +

Register the Name Whisper — ENS Intelligence Layer MCP server in PolicyLayer and add a rule for sweep: 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.

What risk level is sweep? +

sweep is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit sweep? +

Yes. Add a rate_limit block to the sweep 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.

How do I block sweep completely? +

Set action: deny in the PolicyLayer policy for sweep. 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.

What MCP server provides sweep? +

sweep 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.

Enforce policy on every Name Whisper — ENS Intelligence Layer tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.