AI agents call get-token-transfers to retrieve information from Mcp Otc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical token transfer data for a specified address. It performs a read-only query against blockchain data (specifically chain-id 175, an Ethereum fork via Etherscan), with no side effects, no data modification, and no execution of arbitrary code. The blast radius of misuse is minimal—an attacker could enumerate token flows but cannot steal funds, modify data, or execute transactions.
From the tool's definition Tool name is 'get-token-transfers' and description states it 'Get[s] ERC20 token transfers for an Ethereum address' - a retrieval operation that queries blockchain data without modifying state.
Attacks that exploit this kind of access
Get ERC20 token transfers for an Ethereum address. It is categorised as a Read tool in the Mcp Otc MCP Server, which means it retrieves data without modifying state.
Register the Mcp Otc MCP server in PolicyLayer and add a rule for get-token-transfers: 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 Mcp Otc. Nothing to install.
get-token-transfers 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 get-token-transfers 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 get-token-transfers. 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.
get-token-transfers is provided by the Mcp Otc MCP server (otc-ai/mcp-otc). 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 →