Sign a raw hash using the wallet
AI agents invoke raw_sign to trigger actions in Privy 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.
Signing a raw hash is a cryptographic operation that can authorize arbitrary blockchain transactions, messages, or smart contract interactions with no guardrails. An AI agent misusing this tool could sign malicious payloads leading to fund theft, unauthorized contract execution, or other irreversible on-chain consequences.
From the tool's definition 'Sign a raw hash using the wallet' — raw signing of arbitrary hashes bypasses all transaction-level safeguards and structured data validation
Attacks that exploit this kind of access
Sign a raw hash using the wallet. It is categorised as a Execute tool in the Privy MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Privy MCP Server MCP server in PolicyLayer and add a rule for raw_sign: 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 Privy MCP Server. Nothing to install.
raw_sign 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 raw_sign 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 raw_sign. 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.
raw_sign is provided by the Privy MCP Server MCP server (privy-io/privy-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →