// SCAN REPORT

MCP EVM Signer

9 tools. 5 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 1 Jul 2026

5 can modify or destroy data

4 read-only

9 tools total

Community server · catalogue entry verified 01/07/2026

How to control MCP EVM Signer ↓

TOOL MAP

What MCP EVM Signer exposes to your agents

Read (4) Write / Execute (3) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP EVM Signer tools

Financial · Critical deploy-contract Deploying a smart contract is an irreversible on-chain transaction that consumes ETH (gas fees) and permanently publishes code to the blockchain. Financial · Critical send-transaction Sending ETH is an irreversible financial transaction that moves real monetary value. Execute · Critical execute-contract 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 seve Write · Medium create-wallet This tool creates a new Ethereum wallet (key pair), which is a write operation that generates and stores new cryptographic material locally.

5 of MCP EVM Signer's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP EVM Signer

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP EVM Signer, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "deploy-contract": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations

{
  "create-wallet": {
    "limits": [
      {
        "counter": "create-wallet_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "call-contract": {
    "limits": [
      {
        "counter": "call-contract_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP EVM Signer — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP EVM SIGNER →

Instant setup, no code required.

FULL CATALOGUE

All 9 MCP EVM Signer tools

FINANCIAL 2 tools

Financial deploy-contract Deploy a smart contract Financial send-transaction Send ETH to an address

EXECUTE 1 tools

Execute execute-contract Execute a contract method (write)

WRITE 2 tools

Write create-wallet Create a new Ethereum wallet Write import-wallet Import an existing wallet from a private key

READ 4 tools

Read call-contract Call a contract method (read-only) Read check-balance Check the ETH balance of an Ethereum address Read get-transactions Get recent transactions for an Ethereum address Read list-wallets List all saved wallets

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCP EVM Signer

Can an AI agent move money through the MCP EVM Signer MCP server? +

Yes. The MCP EVM Signer server exposes 2 financial tools including deploy-contract, send-transaction. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through MCP EVM Signer? +

The MCP EVM Signer server has 2 write tools including create-wallet, import-wallet. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP EVM Signer.

How many tools does the MCP EVM Signer MCP server expose? +

9 tools across 3 categories: Execute, Read, Write. 4 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on MCP EVM Signer? +

Register the MCP EVM Signer MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP EVM Signer tool call.

Deterministic rules across all 9 MCP EVM Signer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP EVM SIGNER →

Instant setup, no code required.

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