Fetches all ERC20 token approvals for a wallet on a specified chain
AI agents call getApprovals to retrieve information from Token Revoke without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about existing token approvals without modifying, executing code, deleting, or moving funds. It is a query operation that reads blockchain state. While it may surface sensitive information about wallet exposure, the information itself is already publicly readable on-chain, and the tool performs no destructive or state-changing operations.
From the tool's definition The tool name is 'getApprovals' and the description states it 'Fetches all ERC20 token approvals for a wallet on a specified chain.' The verb 'Fetches' and the read-only nature of querying blockchain state indicate no side effects.
Attacks that exploit this kind of access
Fetches all ERC20 token approvals for a wallet on a specified chain. It is categorised as a Read tool in the Token Revoke MCP Server, which means it retrieves data without modifying state.
Register the Token Revoke MCP server in PolicyLayer and add a rule for getApprovals: 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 Token Revoke. Nothing to install.
getApprovals is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the getApprovals 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 getApprovals. 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.
getApprovals is provided by the Token Revoke MCP server (kukapay/token-revoke-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →