AI agents invoke eth_deploy_contract to trigger actions in PortalMCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
While contract deployment itself doesn't directly move funds (Financial) or irreversibly delete data (Destructive), it executes code on a live blockchain network whose consequences are determined by the contract logic and arguments supplied. A malicious contract could perform theft, rug pulls, or other harmful operations.
From the tool's definition Tool name 'eth_deploy_contract' combined with description 'Prepare a transaction to deploy a compiled contract' indicates execution of blockchain contract deployment. Server description confirms 'contract deployment' and 'DeFi operations' capabilities.
Attacks that exploit this kind of access
Prepare a transaction to deploy a compiled contract. It is categorised as a Execute tool in the PortalMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Portal MCP server in PolicyLayer and add a rule for eth_deploy_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 PortalMCP. Nothing to install.
eth_deploy_contract is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the eth_deploy_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 eth_deploy_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.
eth_deploy_contract is provided by the Portal MCP server (portalfnd/portalmcp). 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 →