Manage Foundry contract testing, deployment, and interaction. OPERATIONS: - test: Run Forge tests with fuzzing and gas reports - create: Deploy single contract via forge create - script: Execute Solidity deployment script - call: Call read-only function via cast (FREE) - send: Send state-changing...
AI agents invoke foundry_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 smart contract deployments, runs transactions on blockchain, and executes arbitrary Solidity scripts. While it includes read-only operations (call), the presence of state-changing transactions (send, create, script) and deployment capabilities makes it Execute rather than Read.
From the tool's definition Operations include 'deploy single contract via forge create', 'Execute Solidity deployment script', 'Send state-changing transaction via cast', and 'Start local Anvil node (can fork from network)'.
Attacks that exploit this kind of access
Manage Foundry contract testing, deployment, and interaction. OPERATIONS: - test: Run Forge tests with fuzzing and gas reports - create: Deploy single contract via forge create - script: Execute Solidity deployment script - call: Call read-only function via cast (FREE) - send: Send state-changing transaction via cast - anvil_start: Start local Anvil node (can fork from network) - anvil_stop: Stop Anvil local node AUTO-RESOLUTION: privateKey and rpcUrl are OPTIONAL - if not provided, automatically uses MCP operator account configuration. USE FOR: Testing, deployment, gas analysis, and local development. 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 foundry_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.
foundry_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 foundry_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 foundry_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.
foundry_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 →