AI agents call compute_leaf_hash to retrieve information from Z2 Zetrix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
amount | string | Yes | amount, or tokenId for NFT |
leafKind | integer | Yes | |
recipient | string | Yes | L1 ZTX3 recipient |
rootToken | string | Yes | L1 ZTX3 token, or "" for native |
parentAssertionHash | string | Yes |
Parameters from the server's own tool schema.
This is a cryptographic computation tool used for validation purposes before a withdrawal claim is submitted. It takes parameters (leaf kind and root token) and returns a computed hash value. No data is created, modified, deleted, or financial transactions initiated.
From the tool's definition Tool computes a hash for 'pre-flight verification of a claim' with inputs (leafKind, rootToken). The verb 'compute' and the stated purpose of verification indicate a read-only operation that derives a value without modifying state or triggering external…
Attacks that exploit this kind of access
Compute the Z2 exit-leaf hash (for pre-flight verification of a claim). leafKind: 1=WZETRIX(native), 2=TOKEN(ZTP-20), 3=NFT(ZTP-721). rootToken "" for native. It is categorised as a Read tool in the Z2 Zetrix MCP Server, which means it retrieves data without modifying state.
compute_leaf_hash accepts 5 parameters: amount, leafKind, recipient, rootToken, parentAssertionHash. Required: amount, leafKind, recipient, rootToken, parentAssertionHash. The full parameter table on this page comes from the server's own tool schema.
Register the Z2 Zetrix MCP server in PolicyLayer and add a rule for compute_leaf_hash: 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 Z2 Zetrix. Nothing to install.
compute_leaf_hash 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 compute_leaf_hash 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 compute_leaf_hash. 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.
compute_leaf_hash is provided by the Z2 Zetrix MCP server (z2-zetrix-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
compute_leaf_hash is one line of Z2 Zetrix's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →