get_token_allowances

Enumerate every spender that currently holds a non-zero allowance over the wallet's balance of a specific ERC-20 token on a single EVM chain. Pulls Approval events from Etherscan's logs API filtered to the wallet as owner, dedups by spender (keeping the latest event per spender for provenance), t...

Server VaultPilot MCP vaultpilot-mcp
Category Read
Risk class Low
Parameters 32 required

What get_token_allowances does on VaultPilot MCP

AI agents call get_token_allowances to retrieve information from VaultPilot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
chain string Which EVM chain to scan. Defaults to Ethereum. The same wallet may have different approvals on different chains — you'll need one call per chain to enumerate al
token string Yes ERC-20 contract address. Must be the actual token contract, not a wrapper or aToken. Native coins (ETH / MATIC) have no allowance concept and are intentionally
wallet string Yes EVM wallet address whose approvals you want to enumerate. The tool scans Approval events emitted by `token` where this wallet is the indexed `owner`, then re-re

Parameters from the server's own tool schema.

Why get_token_allowances needs a policy

Even though get_token_allowances only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signalsHandles credentials or secrets (token)

Questions about get_token_allowances

What does the get_token_allowances tool do? +

Enumerate every spender that currently holds a non-zero allowance over the wallet's balance of a specific ERC-20 token on a single EVM chain. Pulls Approval events from Etherscan's logs API filtered to the wallet as owner, dedups by spender (keeping the latest event per spender for provenance), then re-reads the LIVE allowance(owner, spender) for each via Multicall3 and drops anyone whose live value is 0 (revoked or fully consumed). Returns rows sorted by allowance descending, each carrying spender, optional spenderLabel (Aave V3 Pool / Uniswap V3 SwapRouter02 / Lido stETH / etc. resolved against the canonical CONTRACTS table), currentAllowance (raw bigint string), currentAllowanceFormatted (decimal-adjusted, or the literal string "unlimited"), isUnlimited (≥MAX_UINT256 − 0.01% — covers wallets that cap below MAX), and the lastApprovedBlock / lastApprovedTxHash / lastApprovedAt provenance. Top-level unlimitedCount and notes[] flag exposure ("the spender(s) can move your entire balance, including future top-ups; revoke via approve(spender, 0)"). Use this for security audits ("do I have any unrevoked unlimited approvals?"), pre-tx checks ("do I already have allowance for X?"), and revoke-cleanup workflows. v1 EVM-only (Ethereum / Arbitrum / Polygon / Base / Optimism). TRON deferred (different indexer surface); Solana intentionally out of scope (SPL delegation is per-account, not per-mint-per-owner — different question shape). Read-only; no signing, no broadcast. It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.

What parameters does get_token_allowances accept? +

get_token_allowances accepts 3 parameters: chain, token, wallet. Required: token, wallet. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on get_token_allowances? +

Register the VaultPilot MCP server in PolicyLayer and add a rule for get_token_allowances: 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 VaultPilot MCP. Nothing to install.

What risk level is get_token_allowances? +

get_token_allowances is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_token_allowances? +

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

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

get_token_allowances is provided by the VaultPilot MCP server (vaultpilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.