ComposedAlignmentCard
OUTPUT-only variant of `UnifiedAlignmentCard` for the COMPOSED card the server emits on GET `/v1/alignment/{scope}/{id}`, `/effective`, and the `composed` field of preview-compose. Identical to `UnifiedAlignmentCard` except `principal` is optional (a default / org-scope composed card has no agent principal) and `values.declared` / `autonomy.bounded_actions` may be empty (a fresh card declares nothing yet). The strict `UnifiedAlignmentCard` remains the authoring/request contract.
Properties
| Name | Type | Description |
|---|---|---|
| card_version | string | Card schema version (required, non-empty). Current canonical value: `unified/2026-04-26`. |
| content_version | string | Optional. Which default content the card carries, e.g. `mnemom-agent-default/2.1.0` (semver within a lineage). Distinct from `card_version`, the schema version. New agents are born with it; compositio |
| autonomy_mode | string | ADR-039 master switch for the action-policing pipeline (autonomy constraints). Required at the top level post-cutover; the legacy `enforcement.mode` location is rejected. |
| integrity_mode | string | ADR-039 master switch for the values/conscience pipeline (integrity constraints). Required at the top level post-cutover; the legacy `integrity.enforcement_mode` location is rejected. |
| card_id | string | Card row id. Server-assigned on PUT (`ac-{uuid}`). |
| agent_id | string | Target agent id. On PUT, server overwrites to match the URL path. |
| issued_at | string | |
| expires_at | stringnull | |
| principal | object | Required object describing whose authority the agent acts under (ADR-039 Decision 10). |
| values | object | |
| conscience | object | |
| autonomy | object | |
| capabilities | object | |
| enforcement | object | Optional ADR-039 Decision-3 user-facing knobs for unmapped-tool handling. The legacy `mode`, `unmapped_tool_action` and `fail_open` keys are REJECTED by the validator (mode → top-level autonomy_mode; |
| audit | object | |
| tier_modes | object | Per-action risk tier modes for CLPI and AIP. Capped by `autonomy_mode` / `integrity_mode`: a tier can only lower them, and read-tier calls are never withheld. Composition is strictest-wins per tier (e |
| context_fold | object | Owner opt-out of the header-less context fold. Absent means enabled; `enabled: false` turns the fold off for the agent. Composition is off-wins across scopes: an agent can turn it off for itself and a |
| extensions | object | |
| _composition | object | |
| content_hash | string | Response-only: content hash of the composed card (`sha256: |
| version | integer | Response-only: monotonic card version, injected by the GET/PUT response. Server-assigned — do not send on a PUT. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/mnemom-ai/json-schema/mnemom-ai-composed-alignment-card-schema.json",
"title": "ComposedAlignmentCard",
"description": "OUTPUT-only variant of `UnifiedAlignmentCard` for the COMPOSED card the server emits on GET `/v1/alignment/{scope}/{id}`, `/effective`, and the `composed` field of preview-compose. Identical to `UnifiedAlignmentCard` except `principal` is optional (a default / org-scope composed card has no agent principal) and `values.declared` / `autonomy.bounded_actions` may be empty (a fresh card declares nothing yet). The strict `UnifiedAlignmentCard` remains the authoring/request contract.",
"x-generated": "2026-11-18",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/mnemom-ai-openapi.json#/components/schemas/ComposedAlignmentCard",
"type": "object",
"required": [
"card_version",
"agent_id",
"autonomy_mode",
"integrity_mode",
"values",
"autonomy",
"audit"
],
"properties": {
"card_version": {
"type": "string",
"minLength": 1,
"description": "Card schema version (required, non-empty). Current canonical value: `unified/2026-04-26`."
},
"content_version": {
"type": "string",
"description": "Optional. Which default content the card carries, e.g. `mnemom-agent-default/2.1.0` (semver within a lineage). Distinct from `card_version`, the schema version. New agents are born with it; composition carries the agent card's value onto the canonical card."
},
"autonomy_mode": {
"type": "string",
"enum": [
"off",
"observe",
"nudge",
"enforce"
],
"description": "ADR-039 master switch for the action-policing pipeline (autonomy constraints). Required at the top level post-cutover; the legacy `enforcement.mode` location is rejected."
},
"integrity_mode": {
"type": "string",
"enum": [
"off",
"observe",
"nudge",
"enforce"
],
"description": "ADR-039 master switch for the values/conscience pipeline (integrity constraints). Required at the top level post-cutover; the legacy `integrity.enforcement_mode` location is rejected."
},
"card_id": {
"type": "string",
"description": "Card row id. Server-assigned on PUT (`ac-{uuid}`)."
},
"agent_id": {
"type": "string",
"description": "Target agent id. On PUT, server overwrites to match the URL path."
},
"issued_at": {
"type": "string",
"format": "date-time"
},
"expires_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"principal": {
"type": "object",
"description": "Required object describing whose authority the agent acts under (ADR-039 Decision 10).",
"properties": {
"type": {
"type": "string",
"enum": [
"human",
"organization",
"agent",
"unspecified"
]
},
"identifier": {
"type": "string",
"description": "Required (non-empty) when principal.type is not `unspecified`; identifies the human / organization / agent."
},
"relationship": {
"type": "string",
"enum": [
"delegated_authority",
"advisory",
"autonomous"
]
},
"escalation_contact": {
"type": "string"
}
},
"required": [
"type",
"relationship"
]
},
"values": {
"type": "object",
"required": [
"declared"
],
"properties": {
"declared": {
"type": "array",
"items": {
"oneOf": [
{
"type": "string",
"minLength": 1
},
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1
}
},
"additionalProperties": {
"type": "string"
}
}
]
},
"description": "Ordered list of declared values. Phase 1 cards-as-primitive: each entry is either a catalog-v1 ID string (e.g. `'accuracy'`) or a parameterized map carrying optional `intensity` / `domain` / `severity_on_violation` / `scope` (e.g. `{id: 'accuracy', domain: 'financial', severity_on_violation: 'critical'}`)."
},
"definitions": {
"type": "object",
"additionalProperties": {
"type": "object",
"properties": {
"description": {
"type": "string"
},
"priority": {
"type": "number"
}
}
}
},
"conflicts_with": {
"type": "array",
"items": {
"type": "string"
}
},
"hierarchy": {
"type": "string",
"enum": [
"lexicographic",
"weighted",
"contextual"
]
}
}
},
"conscience": {
"type": "object",
"properties": {
"mode": {
"type": "string",
"enum": [
"augment",
"replace"
]
},
"values": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"content"
],
"properties": {
"type": {
"type": "string",
"enum": [
"BOUNDARY",
"FEAR",
"COMMITMENT",
"BELIEF",
"HOPE"
]
},
"content": {
"type": "string"
},
"id": {
"type": "string"
},
"severity": {
"type": "string",
"enum": [
"advisory",
"mandatory"
]
}
}
}
}
},
"required": [
"mode",
"values"
]
},
"autonomy": {
"type": "object",
"required": [
"bounded_actions"
],
"properties": {
"bounded_actions": {
"type": "array",
"items": {
"type": "string"
}
},
"forbidden_actions": {
"type": "array",
"items": {
"type": "string"
}
},
"escalation_triggers": {
"type": "array",
"items": {
"type": "object",
"required": [
"condition",
"action",
"reason"
],
"properties": {
"condition": {
"type": "string"
},
"action": {
"type": "string",
"enum": [
"escalate",
"deny",
"log"
]
},
"reason": {
"type": "string"
}
}
}
},
"max_autonomous_value": {
"type": "object",
"properties": {
"amount": {
"type": "number"
},
"currency": {
"type": "string"
}
}
}
}
},
"capabilities": {
"type": "object",
"additionalProperties": {
"type": "object",
"properties": {
"description": {
"type": "string"
},
"tools": {
"type": "array",
"items": {
"type": "string"
}
},
"required_actions": {
"type": "array",
"items": {
"type": "string"
}
}
}
}
},
"enforcement": {
"type": "object",
"description": "Optional ADR-039 Decision-3 user-facing knobs for unmapped-tool handling. The legacy `mode`, `unmapped_tool_action` and `fail_open` keys are REJECTED by the validator (mode → top-level autonomy_mode; fail_open → gateway env config).",
"properties": {
"allow_unmapped_tools": {
"type": "boolean",
"description": "When true, tools not mapped to a capability are allowed by default."
},
"default_unmapped_severity": {
"type": "string",
"enum": [
"low",
"medium",
"high",
"critical"
],
"description": "Severity assigned to an unmapped tool when allow_unmapped_tools is false."
},
"forbidden_tools": {
"type": "array",
"items": {
"type": "object",
"required": [
"pattern",
"reason",
"severity"
],
"properties": {
"pattern": {
"type": "string"
},
"reason": {
"type": "string"
},
"severity": {
"type": "string",
"enum": [
"critical",
"high",
"medium",
"low"
]
}
}
}
},
"grace_period_hours": {
"type": "integer"
}
}
},
"audit": {
"type": "object",
"required": [
"retention_days",
"queryable"
],
"allOf": [
{
"if": {
"properties": {
"queryable": {
"const": true
}
},
"required": [
"queryable"
]
},
"then": {
"required": [
"query_endpoint"
]
}
}
],
"properties": {
"trace_format": {
"type": "string"
},
"retention_days": {
"type": "integer",
"minimum": 0
},
"queryable": {
"type": "boolean"
},
"query_endpoint": {
"type": "string",
"description": "Required when audit.queryable is true."
},
"tamper_evidence": {
"type": [
"string",
"null"
],
"enum": [
"append_only",
"signed",
"merkle",
null
]
},
"storage": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"local",
"remote",
"distributed"
]
},
"location": {
"type": "string"
}
}
}
}
},
"tier_modes": {
"type": "object",
"additionalProperties": false,
"properties": {
"read": {
"type": "string",
"enum": [
"off",
"observe",
"nudge",
"enforce"
]
},
"in_scope_write": {
"type": "string",
"enum": [
"off",
"observe",
"nudge",
"enforce"
]
},
"out_of_scope": {
"type": "string",
"enum": [
"off",
"observe",
"nudge",
"enforce"
]
},
"protected": {
"type": "string",
"enum": [
"off",
"observe",
"nudge",
"enforce"
]
}
},
"description": "Per-action risk tier modes for CLPI and AIP. Capped by `autonomy_mode` / `integrity_mode`: a tier can only lower them, and read-tier calls are never withheld. Composition is strictest-wins per tier (enforce > nudge > observe > off). Omitted from the composed card when no scope defines it."
},
"context_fold": {
"type": "object",
"additionalProperties": false,
"required": [
"enabled"
],
"properties": {
"enabled": {
"type": "boolean"
}
},
"description": "Owner opt-out of the header-less context fold. Absent means enabled; `enabled: false` turns the fold off for the agent. Composition is off-wins across scopes: an agent can turn it off for itself and an org template can force it off for every agent under it. Omitted from the composed card when no scope defines it."
},
"extensions": {
"type": "object",
"additionalProperties": true
},
"_composition": {
"$ref": "#/$defs/CompositionMetadata"
},
"content_hash": {
"type": "string",
"description": "Response-only: content hash of the composed card (`sha256:<hex>`), injected by the GET/PUT response. Server-assigned — do not send on a PUT."
},
"version": {
"type": "integer",
"description": "Response-only: monotonic card version, injected by the GET/PUT response. Server-assigned — do not send on a PUT."
}
},
"$defs": {
"CompositionMetadata": {
"type": "object",
"description": "System-managed block describing which scope sources merged into the canonical card. Only returned when `?include_composition=true`.",
"properties": {
"canonical_id": {
"type": "string"
},
"composed_at": {
"type": "string",
"format": "date-time"
},
"scopes_applied": {
"type": "array",
"items": {
"type": "object",
"properties": {
"scope": {
"type": "string",
"description": "`platform`, `org:<id>`, or `agent:<id>`."
},
"version": {
"type": "integer"
},
"template_version": {
"type": "integer"
},
"card_id": {
"type": "string"
}
}
}
},
"exemptions_applied": {
"type": "array",
"items": {
"type": "string"
}
},
"source_card_id": {
"type": "string"
},
"source_policy_id": {
"type": "string"
}
}
}
}
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/json-schemas/mnemom-ai-composed-alignment-card"
curl "https://apis.io/api/v1/json-schemas?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.