Skip to content
aerandil.com
GitHub

Read Agent registry entry

GET
/v1/object-types/hospitality.agent_registry_entry/objects/{id}
curl --request GET \
  --url https://api.aerandil.com/v1/object-types/hospitality.agent_registry_entry/objects/2489E9AD-2EE2-8E00-8EC9-32D5F69181C0 \
  --header 'Authorization: Bearer <token>'

Read an existing instance.

Catalog metadata for a first-party or third-party agent, MCP server, or agent skill. Declares maximum action / function / data-class scopes the agent claims to need plus vendor / model / safety metadata. A registry entry is not permission to run — installation enables the agent for a specific tenant / property scope (see agent_installation). The MCP Registry’s server.json is the precedent for storing metadata rather than artifacts; AWS Agent Registry’s curation + approval workflow is the precedent for the review_status gate.

Authorizations

Section titled “Authorizations”

Parameters

Section titled “Parameters”

Path Parameters

Section titled “Path Parameters”
id
required
string format: uuid

Object id (UUID v7, server-generated at create time).

Query Parameters

Section titled “Query Parameters”
branch
string format: uuid

Read through an open branch’s copy-on-first-write overlay view instead of the canonical (main) plane. Does not compose with as_of (422). The branch must exist under the caller’s tenant.

Responses

Section titled “Responses”

200

Section titled “200”

Object found.

Media typeapplication/json
object
created_at
required
string format: date-time
id
required
string format: uuid
object_type
required
Allowed value: hospitality.agent_registry_entry
properties
required
object
agent_key
required
Stable registry key (e.g. `io.github.vendor/recovery-agent`)
string
declared_action_scopes
required
Maximum action scopes the agent claims it may need
Array<string>
declared_data_classes
required
Data classes the agent processes
Array<string>
Allowed values: public operational guest_pii staff_pii payment_metadata regulated_health secrets
declared_function_scopes
required
Maximum function scopes the agent claims it may need
Array<string>
declared_read_scopes
Object types the agent reads, each `objects:<object type>:read` naming a registered type. The ceiling an installation's `enabled_read_scopes` is held to; empty or absent declares no narrowed read set.
Array<string>
declared_risk_tiers
required
Risk tiers the agent claims it may take steps under
Array<string>
Allowed values: read_only internal_write guest_message money_movement identity_or_fraud clinical_or_regulated other_high_risk
definition_document
The runtime-interpreted agent definition (design D3; runtime owns the grammar)
description
Bounded to 2048 characters
string
grounding_scope_ref
scope_key of the `grounding_scope` injected into the retrieval lane (D11)
string
id
required
Registry entry id
string
mcp_server_uri
Canonical remote MCP endpoint when applicable; HTTPS-only enforced by `mcp_remote_requires_https`
string
model_family
Model family when known (e.g. `claude-opus`, `gpt-5`)
string
model_provider
Model provider when known (e.g. `anthropic`, `openai`)
string
obo_scopes
Execute scopes exercisable on behalf of an invoking user (K5 ceiling)
Array<string>
package_references
required
Agent registry entry package references

Package or artifact references using the source registry’s shape

Array<object>
object
digest
string
name
required
string
registry_type
required
string
uri
string
version
string
privacy_url
Publisher privacy / DPA documentation
string
protocols
required
Protocols the agent supports
Array<string>
Allowed values: mcp openapi webhook sdk a2a custom
published_at
Source publish time
string format: date-time
publisher
required
Vendor / publisher namespace
string
registry_record_uri
Source registry URL / ARN / id
string
registry_source
required
Origin of this registry entry
string
Allowed values: aerandil_first_party mcp_registry aws_agent_registry apaleo_agent_hub private_registry manual
review_status
required
Curator review status; only `approved` is installable
string
Allowed values: submitted approved rejected deprecated blocked
reviewed_at
Review timestamp
string format: date-time
reviewed_by
Principal stable id of the reviewer
string
safety_profile
Prompt-injection, data handling, human-review, evaluation metadata
security_url
Security review / SOC2 / vuln disclosure docs
string
title
required
Display name
string
version
required
Agent package / server / skill version
string
provenance

Per-property source attribution and pins. An entry under properties means the property’s current value came from that source (on the source’s own clock, source_updated_at); an entry under pins is a human override protecting the property from sourced writes.

object
pins
object
key
additional properties
object
pinned_at
string format: date-time
pinned_by
object
reason
required
string
properties
object
key
additional properties
object
external_id
string
recorded_at
required
string format: date-time
source
required
string
source_updated_at
string format: date-time
stream
string
scope
required
One of: discriminator: level
object
level
required
string
Allowed value: tenant
Allowed values: tenant
tenant_id
required
string format: uuid
updated_at
required
string format: date-time
version
required
integer
>= 1
Example
{
  "object_type": "hospitality.agent_registry_entry",
  "properties": {
    "declared_data_classes": [
      "public"
    ],
    "declared_risk_tiers": [
      "read_only"
    ],
    "protocols": [
      "mcp"
    ],
    "registry_source": "aerandil_first_party",
    "review_status": "submitted"
  },
  "scope": {
    "level": "tenant"
  }
}

Headers

Section titled “Headers”
ETag
string
/^"\d+"$/

Quoted strong validator (RFC 7232 §2.3) carrying the object’s monotonic version. Informational on the read path — object mutation goes through typed actions on /v1/actions/{action}/apply, not raw CRUD.

404

Section titled “404”

No object with that id (or soft-deleted).