audit_token_approvals
chainpeek: List a wallet's live token approvals and get revoke transactions. For tokens already pulled out use check_wallet_drain; for one allowance use get_allowance. Returns the live ERC-20 and Permit2 allowances of wallet: amount, unlimited, spender code (key-controlled, contract, new contract...
This record as markdown: /tools/dev-tanod-tanod/audit-token-approvals.md
What audit_token_approvals does on Tanod
AI agents call audit_token_approvals to permanently remove resources in Tanod, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
chain | string | Yes | base or ethereum (the chains with built-in USDC and USDT here). |
tokens | object | — | Up to 50 token contracts to audit. Default: USDC, USDT and up to 18 tokens the wallet has sent (from its transfer history). |
wallet | string | Yes | The wallet whose approvals are audited (0x + 40 hex). |
spenders | object | — | Up to 50 spender addresses whose ERC-20 and Permit2 allowances are read directly on every audited token, however old (tokens x spenders at most 200). The full-c |
stale_days | integer | — | An allowance is stale when the spender pulled nothing from the wallet in this many days (1-3,650; default 90). |
lookback_blocks | integer | — | Latest blocks scanned for approval events (0-6,000; default 6,000, about 3.3 hours on Base and 20 hours on Ethereum). 0 scans nothing and checks `spenders` and |
Parameters from the server's own tool schema.
Why audit_token_approvals is rated Critical
An AI agent that decides to call audit_token_approvals doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Tanod is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs audit_token_approvals safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Tanod, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For audit_token_approvals, this is the rule to start with:
audit_token_approvals is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Tanod, apply this rule, and every audit_token_approvals call is checked against it from then on.
Questions about audit_token_approvals
chainpeek: List a wallet's live token approvals and get revoke transactions. For tokens already pulled out use check_wallet_drain; for one allowance use get_allowance. Returns the live ERC-20 and Permit2 allowances of wallet: amount, unlimited, spender code (key-controlled, contract, new contract), newest approval and pull, stale, flags with evidence, and revoke, the unsigned transaction that sets it to 0. Candidates: approval events in the latest 6,000 blocks, Permit2, and spenders. High: unlimited to a key-controlled account. Medium: limited to one, or unlimited to a contract with no code 30 days ago. Low: other unlimited or stale. Older approvals are found only via spenders or Permit2. Bad input is a 422, a failed read a 502 (neither charged). Nothing is signed or sent. Typically 3-15 s. Price: USD 0.005. Free: 10 chain reads per IP per UTC day. Docs: https://tanod.dev/learn/token-approval-audit-api.html. It is categorised as a Destructive tool in the Tanod MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
audit_token_approvals accepts 6 parameters: chain, tokens, wallet, spenders, stale_days, lookback_blocks. Required: chain, wallet. The full parameter table on this page comes from the server's own tool schema.
Register the Tanod MCP server in PolicyLayer and add a rule for audit_token_approvals: 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 Tanod. Nothing to install.
audit_token_approvals is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the audit_token_approvals 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 audit_token_approvals. 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.
audit_token_approvals is provided by the Tanod MCP server (https://tanod.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Tanod, and thousands of servers like it.
Across the catalogue