Mnemom — Trust Ratings for AI Agents

warnings

api.mnemom.ai

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

https://api.mnemom.ai/mcp?profile=directoryWebsiteOAuthMCP 2025-06-18v2.0.0last checked 18 Oct 2026spoke MCP on 100% of 84 checks (30 days)initialize in 495 ms

Will my client connect?

Decided from what the probe found at the endpoint, and from what each client's own documentation says it can complete. Every row carries the day that documentation was read.

✓Claude CodeConnects

The authorization server advertises RFC 7591 registration, so Claude Code can register itself and sign you in through the browser.

claude mcp add --transport http mnemom-trust-ratings-for-ai-agents https://api.mnemom.ai/mcp?profile=directory

Claude Code docs · read on 2026-08-30

✓Claude (claude.ai & Desktop)Connects

The authorization server advertises RFC 7591 registration, so Claude (claude.ai & Desktop) can register itself and sign you in through the browser.

Settings → Connectors → Add custom connector, then paste https://api.mnemom.ai/mcp?profile=directory.

Claude (claude.ai & Desktop) docs · read on 2026-08-30

✓ChatGPTConnects

The authorization server advertises RFC 7591 registration, so ChatGPT can register itself and sign you in through the browser.

Settings → Apps → Advanced settings → Developer mode, then create a connector pointing at https://api.mnemom.ai/mcp?profile=directory.

ChatGPT docs · read on 2026-08-30

✓CursorConnects

The authorization server advertises RFC 7591 registration, so Cursor can register itself and sign you in through the browser.

{
  "mcpServers": {
    "mnemom-trust-ratings-for-ai-agents": {
      "url": "https://api.mnemom.ai/mcp?profile=directory"
    }
  }
}

Cursor docs · read on 2026-08-30

✓VS Code (Copilot)Connects

The authorization server advertises RFC 7591 registration, so VS Code (Copilot) can register itself and sign you in through the browser.

{
  "servers": {
    "mnemom-trust-ratings-for-ai-agents": {
      "type": "http",
      "url": "https://api.mnemom.ai/mcp?profile=directory"
    }
  }
}

VS Code (Copilot) docs · read on 2026-08-30

How to authenticate

Checked against the endpoint by our probe on 18 Oct 2026. These are the capabilities the server advertises, not a prediction about any particular client.

Scheme	OAuth
Issuer	https://api.mnemom.ai
Dynamic client registration	✓Advertised (RFC 7591)
Client ID Metadata Document	✕Not advertised
PKCE	✓S256
Grant types	authorization_code, refresh_token, urn:ietf:params:oauth:grant-type:device_code
Scopes	mcp:read, mcp:write
Protected-resource metadata	✓Published (RFC 9728)
Anonymous access	Handshake succeeds; 15 tools listable
Credentials demanded in prose	✕claim_agent, put_protection_by_agent These tools are listed anonymously and their own descriptions ask for an account or key, but no challenge is issued — so a client has nothing to act on and the refusal arrives as a tool error.
Documentation	https://www.mnemom.ai/auth.md

What the probe found

warningTools needing credentials are listed without a challenge

2 of the 15 tools listed anonymously say in their own descriptions that they need an account or a key (claim_agent, put_protection_by_agent), but the endpoint issued no WWW-Authenticate challenge. The requirement is stated only in prose, so a call reaches the tool and comes back as a tool error instead of an authorization step.

15 tools usable without signing in

The server exposes a public surface before authorization: claim_agent, get_agent, get_reputation, get_reputation_badge, get_started, list_agents, preview_compose_alignment_by_agent, preview_compose_protection_by_agent, put_alignment_by_agent, put_protection_by_agent, report_recipe_fn_fp, scan_trust, search_reputation_directory, verify_reputation, verify_scan.

Tools

claim_agentget_agentget_reputationget_reputation_badgeget_startedlist_agentspreview_compose_alignment_by_agentpreview_compose_protection_by_agentput_alignment_by_agentput_protection_by_agentreport_recipe_fn_fpscan_trustsearch_reputation_directoryverify_reputationverify_scan

Contract history

1 Oct 2026v2.0.02 breaking6 cosmeticinstructions rewritten

Breaking: preview_compose_protection_by_agent, put_protection_by_agent

Instructions rewritten: claim_agent, get_reputation, get_started, list_agents, preview_compose_alignment_by_agent, preview_compose_protection_by_agent, put_alignment_by_agent, put_protection_by_agent. The description an agent follows changed; the callable contract may not have.

30 Sep 2026v2.0.015 cosmeticinstructions rewritten

Instructions rewritten: put_protection_by_agent. The description an agent follows changed; the callable contract may not have.

2 Sep 2026v2.0.0first recorded contract

Watch this server

Save its public contract as a baseline and manage breaking-change email alerts.

Set up a watch

Own this server?

Status badge

Status for a README, from the last probe — cached an hour, so up to seven hours behind the endpoint. Links back to this page.

[![MCP status](https://mcpi.app/servers/mnemom-trust-ratings-for-ai-agents/badge.svg)](https://mcpi.app/servers/mnemom-trust-ratings-for-ai-agents)