Execute state-changing contract function via eth_sendRawTransaction. EXECUTES: Transaction that modifies contract state HANDLES: Function encoding, signing, gas estimation, receipt polling COSTS: Gas fees for execution RETURNS: Transaction hash, receipt, decoded logs AUTO-KEY: privateKey is OPTIO...
AI agents invoke rpc_execute_contract to trigger actions in HashPilot. 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.
This tool executes code (smart contract functions) via blockchain transactions, triggering external operations whose effects depend on supplied arguments. While it modifies state (suggesting Execute rather than pure Read), it is primarily an execution mechanism for arbitrary contract interactions. It is not Destructive because contract state modifications are typically reversible (dependent on the contract logic).
From the tool's definition Tool description states: 'Execute state-changing contract function via eth_sendRawTransaction', 'Transaction that modifies contract state', 'Token transfers, contract interactions, state modifications'.
Attacks that exploit this kind of access
Execute state-changing contract function via eth_sendRawTransaction. EXECUTES: Transaction that modifies contract state HANDLES: Function encoding, signing, gas estimation, receipt polling COSTS: Gas fees for execution RETURNS: Transaction hash, receipt, decoded logs AUTO-KEY: privateKey is OPTIONAL - automatically uses MCP operator account if not provided USE FOR: Token transfers, contract interactions, state modifications. It is categorised as a Execute tool in the HashPilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the HashPilot MCP server in PolicyLayer and add a rule for rpc_execute_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 HashPilot. Nothing to install.
rpc_execute_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 rpc_execute_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 rpc_execute_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.
rpc_execute_contract is provided by the HashPilot MCP server (justmert/hashpilot). 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 →