Check if an address is a smart contract or an externally owned account (EOA)
AI agents call is_contract to retrieve information from SEI MCP Server V2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and reports classification information about blockchain addresses. It performs no writes, executions, deletions, or financial operations. The minimal risk stems from potential information disclosure about contract deployments, but this data is already public on-chain and the tool causes no harm. Classified as Read with low severity.
From the tool's definition Tool description states it 'Check[s] if an address is a smart contract or an externally owned account (EOA)' — a pure query operation with no side effects or state modification.
Attacks that exploit this kind of access
Check if an address is a smart contract or an externally owned account (EOA). It is categorised as a Read tool in the SEI MCP Server V2 MCP Server, which means it retrieves data without modifying state.
Register the SEI MCP Server V2 MCP server in PolicyLayer and add a rule for is_contract: 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 SEI MCP Server V2. Nothing to install.
is_contract 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 is_contract 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 is_contract. 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.
is_contract is provided by the SEI MCP Server V2 MCP server (testinguser1111111/sei-mcp-server). 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 →