execute-contract · MCP EVM Signer MCP: Risk & Policy

WHAT IT DOES

What execute-contract does on MCP EVM Signer

AI agents invoke execute-contract to trigger actions in MCP EVM Signer. 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.

WHY IT NEEDS A POLICY

Why execute-contract needs a policy

While the tool itself is categorized as Write in its description, the broader context of private key management and ability to execute arbitrary contract methods that modify blockchain state elevates this to Execute severity. The tool can trigger external blockchain operations with irreversible financial consequences (gas costs, state changes, token transfers).

From the tool's definition Tool performs contract method execution with write capabilities on EVM blockchains. Description explicitly states '(write)' and name contains 'execute'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute-contract Rate-limited

execute-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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute-contract": {
      "limits": [
        {
          "counter": "execute-contract_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP EVM Signer, so you can run agents against it safely.

FAQ

Questions about execute-contract

What does the execute-contract tool do? +

Execute a contract method (write). It is categorised as a Execute tool in the MCP EVM Signer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute-contract? +

Register the MCP EVM Signer MCP server in PolicyLayer and add a rule for 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 MCP EVM Signer. Nothing to install.

What risk level is execute-contract? +

execute-contract is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute-contract? +

Yes. Add a rate_limit block to the 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.

How do I block execute-contract completely? +

Set action: deny in the PolicyLayer policy for 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.

What MCP server provides execute-contract? +

execute-contract is provided by the MCP EVM Signer MCP server (zhangzhongnan928/mcp-evm-signer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.