Mnemom

What you can ask

• How trust-ready is this website for agents? Scan it, interpret the signed scorecard against the rubric, and fold in any Mnemom-registered agents on the domain.Copy

  Example path scan_trust→verify_reputation

• The sovereignty on-ramp: become a sovereign, accountable agent in five autonomous steps — prove your ground, claim your identity (no human in the loop), declare your values, earn a public signed Trust Rating, and walk away with portable proof. Composes existing tools end to end. Requires auth for the write steps.
• Explain how Mnemom trust scoring works — the reputation rubric (agents) and/or the website-scan rubric — in plain language, from the canonical rubric resources.
• Make YOUR agent trust-ready: claim it, publish/preview its alignment card, set protection posture, and get a concrete checklist. Requires auth.
• Make YOUR website trust-ready: scan it, get a prioritized gap checklist grounded in the rubric (and what it deliberately doesn't measure), then re-scan to verify the loop closed.
• Onboard an agent through the native channel: wrap it at the Dojo gateway, claim it to your org, and declare its starter alignment card. Composes existing tools end to end. Requires auth for the write steps.
• Package a shareable, verifiable proof of an agent's trust: the reputation chain-integrity attestation, an embeddable badge, and the signed agent card.
• Try Mnemom right now — zero-auth, no account. Run the full public trust loop end to end on our live showcase agent (and any site you like) and cryptographically verify every signal, then see how to go further.
• The go/no-go trust briefing: before delegating to another agent, assemble its signed reputation, verify it, review its risk history, and (if a binding is claimed) confirm key ownership.

MCP connector

Server URL

https://api.mnemom.ai/mcpCopy

Login

OAuth

Protocol

MCP 2025-06-18

Instructions

Mnemom is the trust plane for the agentic internet. Live, cryptographic trust signals for AI agents and the sites they act on; everything here is signed and independently verifiable against our public keys, and nothing is fabricated.

New here? Call get_started (zero-auth, no args) for the surface map and auth guide. Two things you can do right now, no account: scan_trust(url) grades any website's agent-trust-readiness (signed scorecard + shareable permalink), and get_reputation(agent_id) / verify_reputation return any registered agent's signed, public Trust Rating. (An agent's risk history is authenticated — get_risk_history needs a Bearer/API-key credential.)

Authenticate (Bearer JWT or X-Mnemom-Api-Key) to claim and manage your own agents — alignment cards, protection posture, and a verifiable Trust Rating that travels.

We deliberately keep integrity- and alignment-internal detail owner-private; the public, signed proof rides in get_reputation.integrity_ratio. Read-only canonical surfaces (the open rubric, value catalog, /for-agents manifesto, signed cards, llms.txt) are exposed as MCP resources.

Verify, don't trust — two DISTINCT paths, don't conflate them. verify_scan does in-band Ed25519 signature verification of a website scorecard against mnemom://iitr/jwks (a verified:true/false verdict + tamper detection). verify_reputation returns a Merkle-root + hash-chain attestation that the rating derives from an unbroken, append-only checkpoint chain (hash_chain_valid), plus a pointer to a signed integrity certificate — a chain-integrity attestation, NOT an in-band signature check. Public keys at mnemom://jwks and mnemom://iitr/jwks.

Tools

Skills

None in the store listings or on the server