Sign a plain text message using EIP-191 personal_sign. Returns signature and signer address.
AI agents invoke sign_message to trigger actions in Agenti. 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.
Signing a message with a private key is a cryptographic execution operation. While it doesn't directly move funds, EIP-191 personal_sign signatures can be used to authorize transactions, authenticate to DeFi protocols, or approve on-chain actions. In the context of a server explicitly designed to 'spend, earn, and receive cryptocurrency,' a misused signing operation could enable unauthorized financial actions.
From the tool's definition Sign a plain text message using EIP-191 personal_sign. Returns signature and signer address.
Documented attack patterns abuse exactly the kind of access sign_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agenti, and nothing reaches the server without passing your rules. This is the rule we recommend for sign_message:
{
"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.
Free to start. No card required.
Sign a plain text message using EIP-191 personal_sign. Returns signature and signer address. It is categorised as a Execute tool in the Agenti MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Agenti 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 Agenti. Nothing to install.
sign_message 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 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.
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.
sign_message is provided by the Agenti MCP server (nirholas/agenti). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 73 Agenti tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
73 Agenti tools catalogued and risk-classified — across an index of 42,500+ MCP servers.