AI agents use eth_generate_contract to create or update resources in PortalMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PortalMCP environment.
This tool produces new contract code artifacts (Write category). While code generation alone is reversible and doesn't directly execute on-chain, it enables contract creation in a blockchain context where generated contracts are likely to be deployed via sibling tools.
From the tool's definition Tool generates Solidity contract code, which creates new smart contract source code artifacts. The description states 'Generate Solidity contract code' indicating code creation/writing capability.
Attacks that exploit this kind of access
Generate Solidity contract code using Claude AI. It is categorised as a Write tool in the PortalMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Portal MCP server in PolicyLayer and add a rule for eth_generate_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_generate_contract is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the eth_generate_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_generate_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_generate_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 →