eth_call · EVM MCP Server MCP: Risk & Policy

WHAT IT DOES

What eth_call does on EVM MCP Server

AI agents invoke eth_call 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.

WHY IT NEEDS A POLICY

Why eth_call needs a policy

eth_call runs arbitrary smart contract code on the EVM. While it does not write state to the blockchain (no transaction is created), it executes code and can trigger complex contract logic. It is read-like in that it has no on-chain side effects, but the 'executes' nature and potential to probe contract state or run arbitrary logic places it in Execute.

From the tool's definition "Executes a new message call immediately without creating a transaction"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

eth_call Rate-limited

eth_call 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": {
    "eth_call": {
      "limits": [
        {
          "counter": "eth_call_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 EVM MCP Server, so you can run agents against it safely.

FAQ

Questions about eth_call

What does the eth_call tool do? +

Executes a new message call immediately without creating a transaction. 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.

How do I enforce a policy on eth_call? +

Register the EVM MCP Server MCP server in PolicyLayer and add a rule for eth_call: 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.

What risk level is eth_call? +

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

Can I rate-limit eth_call? +

Yes. Add a rate_limit block to the eth_call 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 eth_call completely? +

Set action: deny in the PolicyLayer policy for eth_call. 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 eth_call? +

eth_call is provided by the EVM MCP Server MCP server (jamesanz/evm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

eth_call is one line of EVM MCP Server's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →