Execute state-changing functions on a smart contract. Automatically fetches ABI from block explorer if not provided (requires ETHERSCAN_API_KEY). Use this to call any write function on verified contracts. Requires wallet to be configured (via private key or mnemonic).
AI agents invoke write_contract to trigger actions in EVM MCP Server. 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 arbitrary state-changing operations on smart contracts using a configured wallet. While categorized as Execute (not Financial), it has critical severity because it can trigger any contract function including token transfers, ownership changes, minting, burning, or other irreversible on-chain actions depending on the contract and arguments provided.
From the tool's definition Execute state-changing functions on a smart contract... call any write function on verified contracts. Requires wallet to be configured (via private key or mnemonic).
Documented attack patterns abuse exactly the kind of access write_contract gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and EVM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for write_contract:
{
"version": "1",
"default": "deny",
"tools": {
"write_contract": {
"limits": [
{
"counter": "write_contract_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}write_contract stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute state-changing functions on a smart contract. Automatically fetches ABI from block explorer if not provided (requires ETHERSCAN_API_KEY). Use this to call any write function on verified contracts. Requires wallet to be configured (via private key or mnemonic). It is categorised as a Execute tool in the EVM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the EVM MCP Server MCP server in PolicyLayer and add a rule for write_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 EVM MCP Server. Nothing to install.
write_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 write_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 write_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.
write_contract is provided by the EVM MCP Server MCP server (mcpdotdirect/evm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from EVM MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
25 EVM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.