dune_query | PolicyLayer

WHAT IT DOES

What dune_query does on AgentPay x402 — Economic-intelligence layer for AI Agents

AI agents invoke dune_query to trigger actions in AgentPay x402 — Economic-intelligence layer for AI Agents. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why dune_query needs a policy

This tool actively executes queries against an external analytics platform (Dune Analytics). While it reads data, the mechanism is query execution with arbitrary query IDs, making it Execute category. Severity is high because an AI agent could run expensive, resource-intensive, or malicious queries; combined with the pay-per-call USDC payment model, misuse could also drain funds.

From the tool's definition 'Run any Dune Analytics query' — executes arbitrary Dune Analytics queries by ID against live onchain data

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dune_query Rate-limited

dune_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "dune_query": {
      "limits": [
        {
          "counter": "dune_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches AgentPay x402 — Economic-intelligence layer for AI Agents, so you can run agents against it safely.

FAQ

Questions about dune_query

What does the dune_query tool do? +

Run any Dune Analytics query and return live onchain results by query ID. Use fast_only=True for live bots — returns cached result instantly or raises immediately, never blocks. It is categorised as a Execute tool in the AgentPay x402 — Economic-intelligence layer for AI Agents MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on dune_query? +

Register the AgentPay x402 — Economic-intelligence layer for AI Agents MCP server in PolicyLayer and add a rule for dune_query: 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 AgentPay x402 — Economic-intelligence layer for AI Agents. Nothing to install.

What risk level is dune_query? +

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

Can I rate-limit dune_query? +

Yes. Add a rate_limit block to the dune_query 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 dune_query completely? +

Set action: deny in the PolicyLayer policy for dune_query. 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 dune_query? +

dune_query is provided by the AgentPay x402 — Economic-intelligence layer for AI Agents MCP server (romudille-bit/agentpay). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.