Attestation
What may this agent do — and can it prove it hasn’t changed?
Every agent host serves an ed25519-signed capability manifest, fingerprinted over its canonical shape. Drift is detected, not trusted.
SMCP — Service / Sub-agent / Secure Model-Context Protocol — is the MCP-compatible governance layer for AI agents: a versioned, implementable wire spec for how agents declare capabilities, negotiate consent, exchange the minimum necessary data, and settle payment, over MCP and A2A.
Versioning
Governance model
What may this agent do — and can it prove it hasn’t changed?
Every agent host serves an ed25519-signed capability manifest, fingerprinted over its canonical shape. Drift is detected, not trusted.
Exactly which fields of my data does it get, and for how long?
An agent declares the scopes it requests; the human’s durable, time-boxed, revocable grant is the answer. The runtime payload is projected to what was granted.
On what terms — price, hold, review window — does a task run?
Pricing is part of the signed task contract and pinned into the ledger at quote time. A held PaymentIntent, a 48h review window, an HMAC-signed callback.
What did it actually do with my data?
A per-execution ledger and audit log with privacy-preserving anonymization back a customer-readable “what this agent did” view.
How much autonomy has it earned — and who can relax it?
A per-user, per-domain, time-decayed score advances observe → suggest → ask-once → auto. The gate only ever relaxes; nothing tightens silently.
Can a returned value harm the buyer?
Every value an agent returns passes a deny-by-default, fail-closed moderation guard before it ever reaches a human.
Named guarantees
Conformance surface