Mnemom — Trust Ratings for AI Agents
REMOTE · API.MNEMOM.AI · SCANNED SEP 22
Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security66
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (put_alignment_by_agent). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3827 tokens (~147/item across 26 items; 15 tools + 11 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
How do I install the Mnemom — Trust Ratings for AI Agents MCP server?
Mnemom — Trust Ratings for AI Agents is a hosted endpoint at https://api.mnemom.ai/mcp?profile=directory, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.mnemom.ai
claude mcp add --transport http mnemom-mnemom 'https://api.mnemom.ai/mcp?profile=directory'
{
"mcpServers": {
"mnemom-mnemom": {
"url": "https://api.mnemom.ai/mcp?profile=directory"
}
}
} {
"servers": {
"mnemom-mnemom": {
"type": "http",
"url": "https://api.mnemom.ai/mcp?profile=directory"
}
}
} [mcp_servers.mnemom-mnemom] url = "https://api.mnemom.ai/mcp?profile=directory"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mnemom-mnemom": {
"type": "remote",
"url": "https://api.mnemom.ai/mcp?profile=directory",
"enabled": true
}
}
} openclaw mcp add mnemom-mnemom --url 'https://api.mnemom.ai/mcp?profile=directory' --transport streamable-http
mcp_servers:
mnemom-mnemom:
url: "https://api.mnemom.ai/mcp?profile=directory" {
"McpServers": {
"mnemom-mnemom": {
"Transport": "http",
"Url": "https://api.mnemom.ai/mcp?profile=directory"
}
}
} assistant mcp add mnemom-mnemom -t streamable-http -u 'https://api.mnemom.ai/mcp?profile=directory'
{
"mcpServers": {
"mnemom-mnemom": {
"type": "http",
"url": "https://api.mnemom.ai/mcp?profile=directory"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 6 Sept 26 +1
- Stability: fail → pass ▲ security
- 4 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 93.
- 26 Aug 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80.
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 7 Aug 26 0
- A breaking change shipped without a version bump: still 2.0.0 ▼ security
- Tool “verify_agent_binding” was removed ▼ security
- 6 Aug 26 0
- “claim_agent” reworded the description of “hash_proof” cosmetic
1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.
- 5 Aug 26 0
- Stability: 0.30 → fail ▼ security
- A breaking change shipped without a version bump: still 2.0.0 ▼ security
- Schema quality: 118 → 144 ▼ functional
- “preview_compose_alignment_by_agent” added a required parameter “audit”, so existing callers break ▼ functional
- “preview_compose_alignment_by_agent” added a required parameter “autonomy”, so existing callers break ▼ functional
- “preview_compose_alignment_by_agent” added a required parameter “autonomy_mode”, so existing callers break ▼ functional
- “preview_compose_alignment_by_agent” added a required parameter “card_version”, so existing callers break ▼ functional
- “preview_compose_alignment_by_agent” added a required parameter “integrity_mode”, so existing callers break ▼ functional
- “preview_compose_alignment_by_agent” added a required parameter “principal”, so existing callers break ▼ functional
- “preview_compose_alignment_by_agent” added a required parameter “values”, so existing callers break ▼ functional
- “preview_compose_protection_by_agent” added a required parameter “card_version”, so existing callers break ▼ functional
- “preview_compose_protection_by_agent” added a required parameter “mode”, so existing callers break ▼ functional
- “put_alignment_by_agent” added a required parameter “audit”, so existing callers break ▼ functional
- “put_alignment_by_agent” added a required parameter “autonomy”, so existing callers break ▼ functional
- “put_alignment_by_agent” added a required parameter “autonomy_mode”, so existing callers break ▼ functional
- “put_alignment_by_agent” added a required parameter “card_version”, so existing callers break ▼ functional
- “put_alignment_by_agent” added a required parameter “integrity_mode”, so existing callers break ▼ functional
- “put_alignment_by_agent” added a required parameter “principal”, so existing callers break ▼ functional
- “put_alignment_by_agent” added a required parameter “values”, so existing callers break ▼ functional
- “put_protection_by_agent” added a required parameter “card_version”, so existing callers break ▼ functional
- “put_protection_by_agent” added a required parameter “mode”, so existing callers break ▼ functional
- “preview_compose_protection_by_agent” added an optional parameter “protected_surface” cosmetic
- “preview_compose_protection_by_agent” added an optional parameter “screen_surfaces” cosmetic
- “preview_compose_protection_by_agent” added an optional parameter “thresholds” cosmetic
- “preview_compose_protection_by_agent” added an optional parameter “trusted_sources” cosmetic
- “put_protection_by_agent” added an optional parameter “protected_surface” cosmetic
- “put_protection_by_agent” added an optional parameter “screen_surfaces” cosmetic
- “put_protection_by_agent” added an optional parameter “thresholds” cosmetic
- “put_protection_by_agent” added an optional parameter “trusted_sources” cosmetic
- “list_agents” reworded the description of “limit” cosmetic
- “list_agents” reworded the description of “offset” cosmetic
- “preview_compose_alignment_by_agent” reworded the description of “agent_id” cosmetic
- “preview_compose_protection_by_agent” reworded the description of “agent_id” cosmetic
- “put_alignment_by_agent” reworded the description of “agent_id” cosmetic
- “put_protection_by_agent” reworded the description of “agent_id” cosmetic
- “report_recipe_fn_fp” reworded the description of “agent_id” cosmetic
- “report_recipe_fn_fp” reworded the description of “checkpoint_id” cosmetic
- “report_recipe_fn_fp” reworded the description of “recipeId” cosmetic
- “report_recipe_fn_fp” reworded the description of “summary” cosmetic
- “report_recipe_fn_fp” reworded the description of “type” cosmetic
- “preview_compose_alignment_by_agent” dropped the optional parameter “body” cosmetic
- “preview_compose_protection_by_agent” dropped the optional parameter “body” cosmetic
- “put_alignment_by_agent” dropped the optional parameter “body” cosmetic
- “put_protection_by_agent” dropped the optional parameter “body” cosmetic
- “report_recipe_fn_fp” dropped the optional parameter “evidence” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 22 Sept 2026 · Probed https://api.mnemom.ai/mcp?profile=directory
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mnemom.ai | CN=WE1,O=Google Trust Services,C=US | 1 Aug 2026 | 30 Oct 2026 | ECDSA 256 | ECDSA-SHA256 | e10231bd17083cc2135f1284fd9b71cb |
| SANs: mnemom.ai, *.mnemom.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of api.mnemom.ai. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| mnemom.ai. | present | 2371 | 13 | Verified |
| api.mnemom.ai. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000 |
| content-security-policy | default-src 'none'; frame-ancestors 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.mnemom.ai/mcp?profile=directory | Verified | 200 | |
| http (plaintext) | http://api.mnemom.ai/mcp?profile=directory | HTTPS enforced | 301 | https://api.mnemom.ai/mcp?profile=directory |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
claim_agent ~180
Claim a verifiable identity — bind an agent to your organization so its trust and accountability record is provably yours. No human in the loop.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Agent identifier (e.g. smolt-abc123) |
| hash_proof | string | yes | Agent possession proof — either the live birth token (`mnbt_…`) whose row pins this agent's hash, or the full 64-hex SHA-256 digest of `${apiKey}|${agentName}` (or `${apiKey}` for an unnamed singleto… |
| org_id | string | – | Optional. The organization to claim the agent into (e.g. `org-...` or `pers-...`). The caller must be a member of this org (role floor: member). If omitted, the agent is claimed into the caller's per… |
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| claimed | boolean | yes | – |
| claimed_at | string | yes | – |
| org_id | string | yes | The organization the agent was claimed into (echoes the resolved org — the supplied `org_id`, or the caller's personal org when omitted). |
No examples provided.
get_agent ~51
Look up an agent's public identity and trust state by ID — the accountable record other agents and humans can rely on.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Agent identifier (e.g. smolt-abc123) |
| Name | Type | Req | Description |
|---|---|---|---|
| agent_hash | string | – | The canonical public identity hash (first 16 hex chars) used as the gateway lookup key and as the input to verify_agent_binding. Owner projection only. Not a credential and not reversible to one. |
| aip_enforcement_mode | string|null | – | – |
| avatar_url | string|null | – | – |
| caller | string | – | Which projection THIS response is. `org_member` receives the owner field set; `anonymous`/`authenticated` receive the reduced public set (id, name, claimed, created_at, last_seen, status, avatar_url,… |
| claimed | boolean | – | Whether a human or organization has claimed accountability for this agent. On the owner projection this is derived from the ownership column; the owning user's identifier itself is not returned. |
| claimed_at | string|null | – | – |
| containment_status | string|null | – | Containment state of the agent. |
| created_at | string | – | – |
| groups | array | – | Active groups this agent belongs to, name-ordered; `[]` when none. Present on org-fleet rows. |
| id | string | yes | Agent identifier (e.g. smolt-abc123). |
| last_seen | string|null | – | – |
| name | string|null | – | Agent name (2-32 chars, alphanumeric + hyphens). |
| org_id | string|null | – | The agent's organization binding. Required as an input by the org-scoped tools (fleet listing, posture assignment). Identifies an organization, not a person. |
| public | boolean | – | Whether the agent's identity record is publicly discoverable. Distinct from Trust Rating visibility, which is always public. |
| status | string | – | Derived from last_seen (active = seen within the last hour). |
No examples provided.
get_reputation ~104
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: every registered agent's rating is published by standard (the `visibility` field is the reputation-publication axis, distinct from identity-record visibility).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Agent identifier (e.g. smolt-abc123) |
| Name | Type | Req | Description |
|---|---|---|---|
| a2a_trust_extension | object | – | A2A trust extension for interop. Only present on `GET /reputation/{agent_id}` (not on batch/compare rows). |
| agent_id | string | yes | – |
| agent_name | string|null | – | – |
| checkpoint_accounting | object|null | – | Structured breakdown of how checkpoints were counted toward the score. `analyzed` is the scoring population; `excluded` buckets are mutually exclusive and `analyzed + synthetic + insufficient_thinkin… |
| checkpoint_count | integer | yes | – |
| claimed | boolean | – | – |
| components | array | yes | – |
| computed_at | string|null | – | – |
| confidence | string | yes | – |
| grade | string|null | yes | AAA–D or NR. |
| is_eligible | boolean | yes | – |
| next_compute_at | string|null | – | Next scheduled recompute — the 00/06/12/18 UTC cron slot strictly after `computed_at` (`floor(computed_at/6h)*6h + 6h`). Null when `computed_at` is null. |
| score | integer|null | yes | – |
| tier | string|null | – | – |
| trend_30d | number|null | – | – |
| visibility | string | yes | Reputation-publication axis — whether this agent's Trust Rating is published. Every registered agent's reputation is `public` by accountability standard (the default; that is the whole point of a por… |
No examples provided.
get_reputation_badge ~63
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Agent identifier (e.g. smolt-abc123) |
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The agent the badge is for (echoed from the request). |
| badge_url | string | yes | Canonical SVG Trust Rating badge image URL (always on api.mnemom.ai). |
| html_embed | string | yes | Paste-ready HTML badge snippet. |
| markdown_embed | string | yes | Paste-ready Markdown badge snippet. |
| profile_url | string | yes | Human-readable reputation profile page (on www.mnemom.ai). |
| verified_url | string | yes | Public cryptographic verification URL for the rating. |
No examples provided.
get_started ~103
Zero-auth, no-args orientation: who Mnemom is, the surface map, how to authenticate and what it unlocks, and the value tools to try right now (headlining scan_trust + the reputation reads).
| Name | Type | Req | Description |
|---|---|---|---|
| token | string | – | Optional Dojo try-me invite token. When supplied and valid, returns the token-gated dojo briefing manifest (the same content as GET /v1/dojo/try-me/resolve); omit for public orientation. |
| Name | Type | Req | Description |
|---|---|---|---|
| authenticate | object | yes | How to authenticate and what auth unlocks. |
| developer_path | object | yes | The developer hero on-ramp: the npx one-liner plus the intent-named MCP prompt-skills (try-me, onboard_an_agent, become_sovereign). Advertisement only — no functional dependency on those prompts exis… |
| doctrine | string | yes | – |
| showcase_agent | object | yes | A real Mnemom-owned agent the try_now reputation reads target, so the loop runs verbatim. |
| skill_path | object | yes | The two-step on-ramp to declaring and advertising capabilities as A2A skills in a signed, portable AgentCard. |
| sovereignty_path | object | yes | The five-step on-ramp to becoming a sovereign, accountable agent, composed from existing tools. Walked end to end by the become_sovereign MCP prompt. |
| surface_map | object | yes | Stable links to the canonical read-only surfaces. |
| try_now | array | yes | Zero-auth value tools to call right now. |
| value_prop | string | yes | What Mnemom does for an agent. |
| verify | string | yes | How to verify signed artifacts in-band (verify, don't trust). |
| visibility_model | object | yes | Disambiguates the two axes that share the word 'public': reputation-publication visibility (public by standard) vs identity-record visibility (agent.public), plus the caller-context self-description. |
| what_we_keep_private_and_why | string | yes | – |
| who | string | yes | One-line positioning. |
No examples provided.
list_agents ~56
List your agents — List all agents owned by the authenticated user. Supports pagination.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many agents to return, 1-100. |
| offset | integer | – | How many agents to skip, for pagination. |
| Name | Type | Req | Description |
|---|---|---|---|
| agents | array | yes | The caller's agents, reduced to the MCP trust-loop field set. |
| scope | string | yes | Echoes the resolved listing scope. |
No examples provided.
preview_compose_alignment_by_agent ~315
Preview composed alignment (dry run) — Composes the cascade against a hypothetical body at the agent layer and returns conflicts + the composed view. No DB writes. Used by the dashboard editor for live conflict markers.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The agent this card belongs to (e.g. `smolt-abc123`). Identifier only — never place an API key, a secret, an email address, or any other personal data in this field. |
| audit | object | yes | How long this agent's own decision log is kept, and whether it can be queried. Required. (This is the agent's audit policy — it is NOT Mnemom's retention policy for the card itself; see the tool's da… |
| autonomy | object | yes | What the agent may do on its own authority. Required. |
| autonomy_mode | string | yes | Master switch for the action-policing pipeline. Required. `off` disables it; `observe` records only; `nudge` warns; `enforce` blocks. |
| card_version | string | yes | Card schema version. REQUIRED by the server-side validator. Current canonical value: `unified/2026-04-26`. |
| integrity_mode | string | yes | Master switch for the values pipeline. Required. Same four states as `autonomy_mode`. |
| principal | object | yes | Whose authority this agent acts under. Required. |
| values | object | yes | The values this agent declares it is bound by. Required. |
| Name | Type | Req | Description |
|---|---|---|---|
| composition_valid | boolean | yes | True when the composed card is coherence-valid. |
| conflicts_count | integer | yes | Total number of conflicts detected (0 = none). |
| full_report | – | – | Optional pointer to the full /v1 conflict report (method + path). |
| ok | boolean | yes | True when composition succeeded (no blocking conflicts). |
| summary | string | yes | One-line human-readable summary of composition status. |
No examples provided.
preview_compose_protection_by_agent ~334
Preview composed protection (dry run) — Composes the cascade against a hypothetical body at the agent layer and returns conflicts + the composed view. No DB writes. Used by the dashboard editor for live conflict markers.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The agent this card belongs to (e.g. `smolt-abc123`). Identifier only — never place an API key, a secret, an email address, or any other personal data in this field. |
| card_version | string | yes | Card schema version. REQUIRED by the server-side validator. Current canonical value: `protection/2026-04-26`. |
| mode | string | yes | Screening mode for the protection pipeline. Required. `off` disables screening; `observe` records only; `nudge` warns; `enforce` blocks. |
| protected_surface | object | – | The assets and operations this agent must protect. Omit to accept the composed default (empty surface). |
| screen_surfaces | object | – | Which traffic surfaces are screened. Omit to accept the composed defaults. |
| thresholds | object | – | Risk-score cutoffs, each in [0, 1] and ordered warn ≤ quarantine ≤ block. All three are required if this object is sent at all — omit the whole object to accept the composed defaults. |
| trusted_sources | object | – | Sources exempt from screening. Enumerate specific hosts — wildcards are rejected, and a server-side deny-list (public LLM/DNS endpoints, 0.0.0.0/0, ::/0, link-local, multicast) is always applied. |
| Name | Type | Req | Description |
|---|---|---|---|
| composition_valid | boolean | yes | True when the composed card is valid. |
| conflicts_count | integer | yes | Total number of conflicts detected (0 = none). |
| full_report | – | – | Optional pointer to the full /v1 conflict report (method + path). |
| ok | boolean | yes | True when composition succeeded (no blocking conflicts). |
| summary | string | yes | One-line human-readable summary of composition status. |
No examples provided.
put_alignment_by_agent ~334
Publish or replace the alignment manifest — Accepts YAML (`text/yaml`, `application/yaml`) or JSON. Body is the full `UnifiedAlignmentCard`; server-side composition merges it across the platform → org → team → agent cascade and writes the canonical composed card. Requires `Idempotency-Key`. Honor...
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The agent this card belongs to (e.g. `smolt-abc123`). Identifier only — never place an API key, a secret, an email address, or any other personal data in this field. |
| audit | object | yes | How long this agent's own decision log is kept, and whether it can be queried. Required. (This is the agent's audit policy — it is NOT Mnemom's retention policy for the card itself; see the tool's da… |
| autonomy | object | yes | What the agent may do on its own authority. Required. |
| autonomy_mode | string | yes | Master switch for the action-policing pipeline. Required. `off` disables it; `observe` records only; `nudge` warns; `enforce` blocks. |
| card_version | string | yes | Card schema version. REQUIRED by the server-side validator. Current canonical value: `unified/2026-04-26`. |
| integrity_mode | string | yes | Master switch for the values pipeline. Required. Same four states as `autonomy_mode`. |
| principal | object | yes | Whose authority this agent acts under. Required. |
| values | object | yes | The values this agent declares it is bound by. Required. |
| Name | Type | Req | Description |
|---|---|---|---|
| card_id | string | yes | Card ID (ac-{uuid}) of the stored alignment card. |
| issued_at | string | yes | ISO 8601 timestamp when the card was issued/stored. |
| ok | boolean | yes | Always true on successful storage (errors return non-200 status). |
No examples provided.
put_protection_by_agent ~353
Publish or replace the protection manifest — Accepts YAML (`text/yaml`, `application/yaml`) or JSON. Body is the full `UnifiedProtectionCard`; server-side composition merges it across the platform → org → team → agent cascade and writes the canonical composed card. Requires `Idempotency-Key`. Hon...
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The agent this card belongs to (e.g. `smolt-abc123`). Identifier only — never place an API key, a secret, an email address, or any other personal data in this field. |
| card_version | string | yes | Card schema version. REQUIRED by the server-side validator. Current canonical value: `protection/2026-04-26`. |
| mode | string | yes | Screening mode for the protection pipeline. Required. `off` disables screening; `observe` records only; `nudge` warns; `enforce` blocks. |
| protected_surface | object | – | The assets and operations this agent must protect. Omit to accept the composed default (empty surface). |
| screen_surfaces | object | – | Which traffic surfaces are screened. Omit to accept the composed defaults. |
| thresholds | object | – | Risk-score cutoffs, each in [0, 1] and ordered warn ≤ quarantine ≤ block. All three are required if this object is sent at all — omit the whole object to accept the composed defaults. |
| trusted_sources | object | – | Sources exempt from screening. Enumerate specific hosts — wildcards are rejected, and a server-side deny-list (public LLM/DNS endpoints, 0.0.0.0/0, ::/0, link-local, multicast) is always applied. |
| Name | Type | Req | Description |
|---|---|---|---|
| card_id | string | yes | Card ID (pc-{uuid}) of the stored protection card. |
| issued_at | string | yes | ISO 8601 timestamp when the card was issued/stored. |
| ok | boolean | yes | Always true on successful storage (errors return non-200 status). |
No examples provided.
report_recipe_fn_fp ~271
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Optional. The agent the report concerns. Identifier only. |
| checkpoint_id | string | – | Optional. The related integrity checkpoint, so the reviewer can correlate. Identifier only. |
| recipeId | string | yes | The detection recipe the report is filed against (the one that misfired or failed to fire). Identifier only. |
| summary | string | yes | A short description of what the recipe got wrong — what it flagged, or what it missed, and why that was incorrect. DESCRIBE the misfire; do NOT paste the conversation, the prompt, the raw payload or… |
| type | string | yes | `fn` = false negative (the recipe should have fired). `fp` = false positive (it fired on legitimate behaviour). |
| Name | Type | Req | Description |
|---|---|---|---|
| candidate_id | string | yes | – |
| ok | boolean | yes | – |
| related_recipe_id | string | yes | – |
| type | string | yes | – |
No examples provided.
scan_trust ~202
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 isittrustready scanner; the Ed25519 signature + permalink are preserved verbatim. Rubric + docs: https://www.isittrustready.ai/rubric and https://docs.mnemom.ai/.
| Name | Type | Req | Description |
|---|---|---|---|
| fresh | boolean | – | Force a fresh re-scan instead of the cached result (results are cached up to 24h; the engine rate-limits re-scans). Equivalent to the scanner's rescan flag. |
| url | string | yes | Domain or URL to scan, e.g. "example.com" or "https://example.com". |
| Name | Type | Req | Description |
|---|---|---|---|
| access | object | – | The independent Access/discoverability axis (never blended with Trust). Present from the two-axis rubric (0.3.0+). |
| cached | boolean | – | True when served from the scanner's 24h cache rather than a fresh scan. |
| categories | array | – | Trust-axis categories with per-category scores + checks. |
| grade | string | yes | Trust letter grade (A+…F). |
| permalink | string | – | Shareable /r/ permalink (only on /r/ responses; transport field). |
| rubricVersion | string | – | Rubric version (e.g. "0.4.0"). |
| scannedAt | string | – | When this scorecard was produced. Results are cached up to 24h — pass fresh:true to scan_trust to force a re-scan. |
| schema | string | yes | iitr-scan schema version string (e.g. "iitr-scan/v0.N"). |
| score | number | yes | 0–100 weighted overall TRUST score. |
| signature | object | yes | Ed25519 signature over the canonical result (transport field; stripped before verify). |
| target | string | yes | Normalized host that was scanned. |
| verification | object | – | Self-describing in-band verification block {alg, kid, jwks, canonicalization} — how to verify this scorecard's signature. Self-describing, so signed-EXCLUDED (stripped before verify). |
No examples provided.
search_reputation_directory ~199
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.
| Name | Type | Req | Description |
|---|---|---|---|
| confidence | string | – | Filter to agents at a given reputation-confidence level (driven by how much evidence backs the score). |
| grade | string | – | Filter to one grade (e.g. `AAA`, `B`, `NR`). |
| page | integer | – | 1-based page number for pagination. Default 1. |
| per_page | integer | – | Number of results per page. 1–100, default 20. |
| q | string | – | Name search (ilike) or agent-id prefix match. |
| sort | string | – | Result ordering. Default "score" (highest-rated first); other supported keys order by recency or name. |
| Name | Type | Req | Description |
|---|---|---|---|
| agents | array | yes | – |
| page | integer | yes | – |
| per_page | integer | yes | – |
| total | integer | yes | – |
No examples provided.
verify_reputation ~104
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 check (that parity is verify_scan, for website scorecards).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Agent identifier (e.g. smolt-abc123) |
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| computed_at | string | yes | – |
| grade | string | yes | – |
| score | number | yes | – |
| verification | object|null | yes | – |
No examples provided.
verify_scan ~182
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.isittrustready.ai/rubric and https://docs.mnemom.ai/.
| Name | Type | Req | Description |
|---|---|---|---|
| scan | object | – | A scan scorecard previously returned by scan_trust (or iitr's /r/ JSON), passed back verbatim to verify. Same shape as scan_trust's result; the signature is checked against mnemom://iitr/jwks. |
| url | string | – | Alternatively, a domain/URL to re-scan and then verify. |
| Name | Type | Req | Description |
|---|---|---|---|
| algorithm | string | yes | Always "Ed25519". |
| canonicalization | string | yes | The exact canonicalization used (so the verdict is reproducible). |
| key_id | string|null | yes | The signing key id (kid) checked. |
| reason | string | – | Why verification failed or could not be evaluated (absent when verified). |
| scorecard | object | – | The scorecard verified (present when re-scanned via `url`). |
| verified | boolean | yes | True iff the signature verifies against the in-band JWKS. |
No examples provided.
What is the Mnemom — Trust Ratings for AI Agents MCP server?
Mnemom — Trust Ratings for AI Agents is an MCP server listed in the public MCP registry as io.github.mnemom/mnemom. Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge. This page covers its hosted endpoint (https://api.mnemom.ai/mcp?profile=directory).
Is the Mnemom — Trust Ratings for AI Agents MCP server safe to use?
Mnemom — Trust Ratings for AI Agents scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Mnemom — Trust Ratings for AI Agents MCP server expose?
Mnemom — Trust Ratings for AI Agents exposes 15 tools: claim_agent, get_agent, get_reputation, get_reputation_badge, get_started, and 10 more. Their descriptions and schemas cost roughly 2,851 tokens of context every time the server is loaded.
Does the Mnemom — Trust Ratings for AI Agents MCP server require authentication?
No. We connected to Mnemom — Trust Ratings for AI Agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Mnemom — Trust Ratings for AI Agents MCP server still maintained?
Mnemom — Trust Ratings for AI Agents is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.