Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Scored across 9 tools
Each tool targets a distinct operation: proof creation, retrieval, hashing, verification, referral resolution, and separate capability/stat reads. The read-only capability tools are clearly differentiated from one another by their specific domain (network, passport product, wallet).
All tool names share the accord_trace_ prefix and use snake_case, which is consistent. However, some names are verb-object (create_proof, resolve_referral) while capability and stats tools omit a verb (network_capabilities, wallet_capabilities), creating a minor stylistic inconsistency.
Nine tools is well within the ideal range and appropriate for the server's mixed proof and affiliate-network domain. Each tool covers a distinct capability without redundancy, and the count feels intentional rather than bloated or thin.
The proof lifecycle is well covered with create, get, verify, and hash operations, and the network side provides capabilities, stats, and referral resolution. Minor gaps exist, such as no listing/searching of proofs or enrollment actions, but the read-only boundaries are clearly described and likely intentional.
Create an AccordTrace hash-bound service record. If issuer signing is configured, the proof also carries an Ed25519 issuer signature. Submitted content is not stored.
Inputs: data (required), metadata.
Retrieve public non-secret AccordTrace proof metadata by proof ID.
Inputs: proof_id (required).
Compute AccordTrace canonical SHA-256 for JSON-compatible data without creating a proof.
Inputs: data (required).
Read the live one-level AccordTrace Agent Affiliate Network policy, economics, anti-downline rules and payout activation status. Read-only; it does not enroll or attribute an agent.
Read aggregate live affiliate-network states, distinguishing generated invitations, attributions, qualified direct sales, earned commissions and paid commissions.
Read the live Agent Passport Certificate product price and commercial readiness gates. Read-only; it never initiates checkout.
Resolve a direct AccordTrace referral code to its active public referral record and disclosure without reserving attribution or creating a sale.
Inputs: referral_code (required).
Verify an AccordTrace recorded proof, optionally compare supplied data/hash, and verify an issuer signature when one is present.
Inputs: proof_id (required), data, hash.
Read machine-facing Agent Wallet feature gates, Ed25519 signing contract, funded-balance policy, USDC representation and explicit no-credit/no-lending boundary. Read-only; it never creates a wallet or moves funds.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Policy-aware AI execution, verification, cost, and trajectory evidence for agents.
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Signed, publicly logged records of what your AI agent did, with proofs anyone can check offline.
Add one secure layer between your agents and this server.
