Verifiable random function — deterministic, publicly verifiable randomness bound to your seed and signed by the 2s key. proof = deterministic EIP-191 signature over the seed (same seed always yields the same proof, so the outcome cannot be re-rolled or cherry-picked); random = keccak256(proof), a...
AI agents call crypto.vrf to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool generates and returns a deterministic random value (and its proof) given a seed. It reads/computes a cryptographic output without modifying, deleting, or transacting any data. The pay-per-call billing is handled by the x402 protocol at the server layer, not by this tool itself. Severity is low because misuse only results in a meaningless random number being generated.
From the tool's definition Verifiable random function — deterministic, publicly verifiable randomness bound to your seed and signed by the 2s key. proof = deterministic EIP-191 signature over the seed
Attacks that exploit this kind of access
Verifiable random function — deterministic, publicly verifiable randomness bound to your seed and signed by the 2s key. proof = deterministic EIP-191 signature over the seed (same seed always yields the same proof, so the outcome cannot be re-rolled or cherry-picked); random = keccak256(proof), a uniform 32-byte value. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for crypto.vrf: 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 Mcp. Nothing to install.
crypto.vrf is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crypto.vrf 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 crypto.vrf. 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.
crypto.vrf is provided by the MCP server (@2sio/mcp). 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 →