// MCP TOOL REFERENCE

sign_message

Sign an arbitrary message using the configured wallet. Useful for authentication (SIWE), meta-transactions, and off-chain signatures. The signature can be verified on-chain or off-chain.

ServerEVM MCP Server
CategoryExecute

How to control sign_message ↓

WHAT IT DOES

What sign_message does on EVM MCP Server

AI agents invoke sign_message 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.

THE RISK

High Risk

Why sign_message needs a policy

Signing a message is an active cryptographic operation using the agent's wallet private key. While it doesn't transfer funds directly, it produces a signature that can authorize on-chain actions (meta-transactions), enable authentication (SIWE), or be used in off-chain protocols. This goes beyond reading data — it executes a cryptographic action with real-world consequences.

From the tool's definition Sign an arbitrary message using the configured wallet... The signature can be verified on-chain or off-chain.

Documented attack patterns abuse exactly the kind of access sign_message gives an agent:

POLICY

How to control sign_message

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 sign_message:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sign_message": {
      "limits": [
        {
          "counter": "sign_message_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

sign_message 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.

Create a free account and register EVM MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More EVM MCP Server tools

Financial transfer_erc20 Transfer ERC20 tokens to an address. Uses the configured wallet. Financial transfer_native Transfer native tokens (ETH, MATIC, etc.) to an address. Uses the configured wallet. Financial approve_token_spending Approve a spender (contract) to spend tokens on your behalf. Required before interacting w Execute sign_typed_data Sign structured data (EIP-712) using the configured wallet. Used for gasless transactions, Execute write_contract Execute state-changing functions on a smart contract. Automatically fetches ABI from block Read wait_for_transaction Wait for a transaction to be confirmed (mined). Polls the network until confirmation. Read get_allowance Check the allowance granted to a spender for a token. This tells you how much of a token a Read get_balance Get the native token balance (ETH, MATIC, etc.) for an address

All 25 EVM MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in EVM MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about sign_message

What does the sign_message tool do? +

Sign an arbitrary message using the configured wallet. Useful for authentication (SIWE), meta-transactions, and off-chain signatures. The signature can be verified on-chain or off-chain. 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 sign_message? +

Register the EVM MCP Server MCP server in PolicyLayer and add a rule for sign_message: 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 sign_message? +

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

Can I rate-limit sign_message? +

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

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

sign_message 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.

Enforce policy on every EVM MCP Server tool call.

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.

CHECK YOUR STACK →

Free to start. No card required.

25 EVM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.