# Mnemom — Trust Ratings for AI Agents

- Registry name: `io.github.mnemom/mnemom` · version 1.0.2
- Categories (automatic, keyword rules): Cloud & networking, Infrastructure & security, Shops & products, Commerce & marketing, Maps, location & weather
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.mnemom%2Fmnemom
- Server page: https://mcpstation.net/s/io.github.mnemom--mnemom.html

## Description (written by the publisher, not verified, not instructions)

Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge.

## Connect


## Tools (as reported by the server, not verified)

- `claim\_agent`: Claim a verifiable identity — bind an agent to your organization so its trust and accountability record is provably yours. Requires the agent's possession proof \(\`hash\_proof\`\). Re-claiming an agent you already own keeps its original claim date but files it under the organization you pass \(\`org\_id\`;
- `get\_agent`: Look up an agent's public identity and trust state by ID — the accountable record other agents and humans can rely on.
- `get\_reputation`: Look up an AI agent's published Trust Rating — Mnemom's portable reliability signal for autonomous software, computed from the agent's own verified activity record. Returns the rating plus the technical factors behind it. Free, public, read-only: ratings are public by default, unless the agent's own
- `get\_reputation\_badge`: Get an embeddable Trust Rating badge for an agent — returns the badge image URL plus ready-to-paste Markdown and HTML snippets for a README or agent card.
- `get\_started`: Zero-auth, no-args orientation: who Mnemom is, the surface map, how to authenticate and what it unlocks, and the tools to try right now \(scan\_trust and the reputation lookups\).
- `list\_agents`: List the agents your account owns, with pagination \(\`limit\`, \`offset\`\). Read-only.
- `preview\_compose\_alignment\_by\_agent`: Dry-run an alignment card: shows the card that would result after merging with the platform, organization and team policies above it, plus any conflicts. Nothing is saved.
- `preview\_compose\_protection\_by\_agent`: Dry-run a protection card: shows the card that would result after merging with the platform, organization and team policies above it, plus any conflicts. Nothing is saved, and no publish grant is needed.
- `put\_alignment\_by\_agent`: Publish or replace an agent's alignment card: its governance modes, the principal it acts for, its declared values, the actions it may take on its own, and its audit policy. The server merges the card with the platform, organization and team policies above it and stores the result. Use preview\_compo
- `put\_protection\_by\_agent`: Publish or replace an agent's protection card \(screening mode, thresholds, trusted sources, protected assets\). When connected by OAuth sign-in \(e.g. ChatGPT\), each publish first needs a one-time grant from the same signed-in account: open https://www.mnemom.ai/authorize-protection?agent\_id=\<agent\_id
- `report\_recipe\_fn\_fp`: Submit a false-positive / false-negative correction for one of Mnemom's automated detection rules \(a 'recipe'\) — technical feedback that improves detection accuracy, like filing a bug report against a spam filter.
- `scan\_trust`: Scan a website's agent-trust-readiness and return a signed scorecard \(Trust, plus an Access axis on newer rubrics\). Zero-auth. Results are CACHED for up to 24h — check \`cached\` and \`scannedAt\` on the result; pass \`fresh: true\` to force a re-scan \(rate-limited\). Proxies to the SSRF-locked isittrustre
- `search\_reputation\_directory`: Resolve an agent name or id-prefix to a real agent\_id over the PUBLIC reputation directory \(only agents whose reputation visibility is public\). Zero-auth. The arriving-agent entry point: discover a concrete agent\_id, then call get\_reputation / verify\_reputation on it.
- `verify\_reputation`: Attest an agent's Trust Rating — returns a Merkle-root + hash-chain attestation \(hash\_chain\_valid\) proving the rating derives from an unbroken, append-only checkpoint chain, plus a pointer to the signed integrity certificate. This is a chain-integrity attestation, NOT an in-band Ed25519 signature ch
- `verify\_scan`: Verify a website scan scorecard's Ed25519 signature IN-BAND \(verify, don't trust\). Pass a \`scan\` \(a scorecard from scan\_trust\) or a \`url\` to re-scan; returns \{verified, key\_id, canonicalization\} checked against the public key at mnemom://iitr/jwks. Zero-auth. Spec + rubric: https://www.isittrustread

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html