Skip to main content
Glama

Ariadne Nexus Provenance & Underwriting MCP

Ed25519 Zero-PII Provenance Certificate & Merkle Verifier

verify_zk_provenance_proof
Read-onlyIdempotent

Verifies an ariadne-zk-ed25519-v1 (ZK_PROV_V1) provenance certificate across Ed25519 signature validity, zero-PII enforcement, signed claim parity, optional pinned oracle key, and optional 0x01 SHA-256 custodial Merkle recomputation. Use when: auditing a certificate from generate_zk_provenance_proof before policy bind or loan closing. Do not use when: generating a new proof (use generate_zk_provenance_proof instead), checking a manifest digest (use verify_asset_hash instead), or auditing portfolio LTV cap compliance (use verify_underwriting_compliance instead). Behavior: Read-only, stateless cryptographic check (p99=18ms; free discovery tier at 60 RPM without billing).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "zk_attestation_certificate": "<zk_attestation_certificate>"
    },
    "name": "verify_zk_provenance_proof"
  }
}

Input Schema

NameRequiredDescriptionDefault
asset_idNoOptional outer asset_id cross-checked against the signed asset claim.
policy_refNoOptional outer policy_ref cross-checked against the signed policy claim.
custody_event_hashesNoOptional ordered custodial SHA-256 digests used to independently recompute and verify the 0x01-prefixed Merkle root.
pinned_oracle_pubkey_b64NoOptional out-of-band pinned base64 Ed25519 oracle public key enforced during verification.
optical_forensic_score_bpsNoOptional outer optical score (0-10000 bps) cross-checked against signed optical_bps.
zk_attestation_certificateYesSigned ZK_PROV_V1 certificate object emitted by generate_zk_provenance_proof.
title_lien_clearance_merkle_rootNoOptional outer 64-hex Merkle root cross-checked against signed merkle_root.

Output Schema

NameRequiredDescriptionDefault
tierYesCommercial execution tier ("free_discovery").
toolYesExecuted tool identifier ("verify_zk_provenance_proof").
schemeYesEvaluated certificate scheme identifier.
verifiedYesTrue only when signature, zero-PII, claims, pinned key, and Merkle checks all pass.
failure_codeYesVerification disposition code ("NONE" when verified is true).
signed_claimsYesParsed key-value claims from the signed ZK_PROV_V1 statement.
failure_detailNoDiagnostic explanation populated when verified is false.
signature_validYesTrue when the Ed25519 signature over public_statement verified cleanly.
zero_pii_confirmedYesTrue when seller_pii_exposed is strictly false.
pinned_key_enforcedYesTrue when pinned_oracle_pubkey_b64 was supplied and matched.
execution_latency_msYesServer-side execution duration in milliseconds.
oracle_pubkey_sha256_hexYesLowercase 64-hex SHA-256 fingerprint of the raw 32-byte Ed25519 public key.
oracle_pubkey_ed25519_b64YesBase64 Ed25519 public key extracted from the certificate.
merkle_chain_independently_recomputedYesTrue when custody_event_hashes were supplied and matched signed merkle_root.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, but the description still adds real value: it states the operation is stateless, gives p99=18ms, and discloses the free discovery tier at 60 RPM without billing, which matters for retry/batching decisions. The gap is failure semantics: it never says whether a failed check throws an error or returns a validity verdict, so an agent cannot predict the failure path from the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the verification scope, then cleanly segmented into Use when / Do not use when / Behavior, which is exactly the structure an agent needs. The opening sentence is very dense with jargon (0x01 SHA-256 custodial Merkle recomputation) and slightly overpacked, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter tool with a nested certificate object, the description covers purpose, routing, safety profile, and performance, and an output schema exists so return shape need not be described. What is missing is outcome semantics on verification failure and any guidance on constructing custody_event_hashes ordering for Merkle recomputation, the one area where a caller can silently get a false negative.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with a nested certificate object fully documented, so the schema does the heavy lifting and the baseline is 3. The description does add framing that the outer fields (pinned key, Merkle digests, asset/policy/score cross-checks) are parity checks against signed claims, but it does not explain ordering, Merkle prefix handling, or what happens when an optional cross-check mismatches.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (verifies) and a precisely scoped resource (ariadne-zk-ed25519-v1 / ZK_PROV_V1 provenance certificate), then enumerates the exact checks performed: Ed25519 signature validity, zero-PII enforcement, signed claim parity, pinned oracle key, and 0x01 Merkle recomputation. An agent can distinguish this from generate_zk_provenance_proof and the two other verify_* siblings on the name plus first sentence alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'Use when' clause pins the trigger to auditing a certificate from generate_zk_provenance_proof before policy bind or loan closing. The 'Do not use when' clause names three concrete alternatives (generate_zk_provenance_proof, verify_asset_hash, verify_underwriting_compliance) with the condition that selects each, leaving no routing ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources