AI agents call get-contract-abi 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.
Contract ABIs are public blockchain data used for interaction purposes. Retrieving an ABI is a simple query operation with no side effects, no code execution, and no financial impact. It matches the 'Read' category definition: 'retrieves or queries data; no side effects'. The low severity reflects that misuse cannot cause damage—an AI agent cannot harm systems or funds by requesting contract ABIs.
From the tool's definition Tool name 'get-contract-abi' and description 'Get the ABI for a smart contract' indicate a read-only operation that retrieves contract metadata (Application Binary Interface) without modifying state or executing code.
Attacks that exploit this kind of access
Get the ABI for a smart contract. 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-contract-abi: 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-contract-abi 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-contract-abi 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-contract-abi. 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-contract-abi 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 →