AI agents call eth_call_contract to retrieve information from PortalMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries blockchain state through a read-only contract function call. It has no capacity to modify, destroy, or move assets. While the sibling tools on this server include write operations (eth_create_token, eth_deploy_contract, eth_create_nft_collection) and financial operations, this specific tool is explicitly constrained to read-only semantics.
From the tool's definition Tool name 'eth_call_contract' and description explicitly states 'Call a read-only function on an Ethereum smart contract'. The term 'read-only' is the definitive indicator that this operation retrieves data without side effects.
Attacks that exploit this kind of access
Call a read-only function on an Ethereum smart contract. It is categorised as a Read tool in the PortalMCP MCP Server, which means it retrieves data without modifying state.
Register the Portal MCP server in PolicyLayer and add a rule for eth_call_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_call_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 eth_call_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_call_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_call_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 →