Import Agent Unified

{ "agent": { "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "agent_name": "<string>", "model_name": "<string>", "team_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "created_by": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "created_at": 123, "updated_at": 123, "agent_url": "<string>", "hub": "custom", "api_key": "<string>", "agent_system_prompt": "<string>", "rate_limit_requests_per_minute": 100, "status": "active", "access_level": "black_box", "agent_params": { "temperature": 123, "top_p": 123, "max_tokens": 123, "timeout": 123, "rag_params": {}, "function_route_params": {} }, "mcp_config": { "proxy_url": "<string>", "access_level": "read", "server_urls": [ "<string>" ] }, "delegated_agents": [ { "url": "<string>", "agent_card_url": "<string>", "name": "<string>", "capabilities": [ "<string>" ] } ], "white_box_config": { "source_code": "<string>", "repo_url": "<string>", "github_username": "<string>", "repo_branch": "<string>", "entry_point": "<string>" }, "agent_metadata": { "role": "<string>", "job_description": "<string>", "version": "<string>", "author": "<string>", "tags": [ "<string>" ] }, "purpose": "<string>", "protocol": "chat_completions", "test_score": "<string>", "last_tested_by": "<string>", "evaluated_harnesses": [ "<string>" ], "last_evaluated_at": 123, "protection_status": "unprotected", "trust_stage": "registered", "trusted_at": 123, "ttt_days": 123, "dome_config_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "dome_manually_configured": false, "import_metadata": { "source": "manual", "source_url": "<string>", "imported_at": 123, "original_format": "<string>" }, "capabilities": { "streaming": false, "push_notifications": false, "code_execution": false, "memory": false, "delegation": false, "tools": [ "<string>" ] }, "skills": [ { "id": "<string>", "name": "<string>", "description": "<string>", "input_modes": [ "<string>" ], "output_modes": [ "<string>" ] } ], "latest_evaluation": { "evaluation_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "overall_score": 123, "reliability_score": 123, "security_score": 123, "safety_score": 123, "completed_at": 123 } }, "access_level": "<string>", "warnings": [], "external_id": "<string>", "identity_provider": "<string>" }

Body

application/json

Unified request model for agent import.

Supports five input methods (exactly one required), each with deterministic access level:

Input Method	Mode	Access Level	Description
agent_url	Remote	black_box	Just an endpoint URL to call
agent_card	Local	grey_box	Upload agent configuration/card JSON
source_code	Local	white_box	Upload agent source code files

agent_url

string | null

Remote black_box: Agent endpoint URL to call (e.g., https://api.example.com/agent)

agent_card

Agent Card · object

Local grey_box: Upload agent configuration/card JSON directly

source_code

SourceCodeUpload · object

Local white_box: Upload agent source code files directly

Hide child attributes

source_code.files

Files · object

required

Map of filename to content. Use 'main.py' for single file uploads.

Hide child attributes

source_code.files.{key}

string

source_code.entry_point

string

default:main.py

Main entry point file (must exist in files)

source_code.framework

string

default:unknown

Framework identifier (for informational purposes only)

source_code.agent_name

string | null

Agent name (extracted from code if not provided)

source_code.model_name

string | null

Model name used by the agent

source_code.description

string | null

Agent description

source_code.system_prompt

string | null

System prompt if known

source_code.tools

string[] | null

List of tools/functions the agent uses

framework

string | null

Framework identifier (for informational purposes only)

entry_point

string | null

For white box: path to main file

override_name

string | null

Override agent name

rate_limit_requests_per_minute

integer

default:100

Required range: x >= 1

api_key

string | null

API key for the agent

external_id

string | null

External identity ID

identity_provider

string | null

Identity provider name

idp_metadata

Idp Metadata · object

IdP-specific metadata

Response

Successful Response

Response model for unified import.

agent

Agent · object

required

Agent domain model.

Hide child attributes

agent.id

string<uuid>

required

agent.agent_name

string

required

agent.model_name

string

required

agent.team_id

string<uuid>

required

agent.created_by

string<uuid>

required

agent.created_at

integer

required

agent.updated_at

integer

required

agent.agent_url

string | null

agent.hub

string

default:custom

agent.api_key

string | null

agent.agent_system_prompt

string | null

agent.rate_limit_requests_per_minute

integer

default:100

Rate limit for API requests per minute

Required range: x >= 1

agent.status

enum<string>

default:active

Agent status values.

Available options:

draft,

creating,

active,

under_review,

deprecated,

archived,

pending,

rejected

agent.access_level

enum<string>

default:black_box

Access level for agent analysis.

Black Box: URL only - behavioral testing only Grey Box: Agent configuration - structure/capabilities analysis White Box: Source code access - full code + sandbox runtime analysis

Available options:

black_box,

grey_box,

white_box

agent.agent_params

AgentParams · object

Model parameters for agent configuration.

Hide child attributes

agent.agent_params.temperature

number | null

agent.agent_params.top_p

number | null

agent.agent_params.max_tokens

integer | null

agent.agent_params.timeout

integer | null

agent.agent_params.rag_params

Rag Params · object

agent.agent_params.function_route_params

Function Route Params · object

agent.mcp_config

MCPConfig · object

MCP (Model Context Protocol) proxy configuration.

Hide child attributes

agent.mcp_config.proxy_url

string<uri> | null

Required string length: 1 - 2083

agent.mcp_config.access_level

enum<string> | null

MCP (Model Context Protocol) access level values.

Available options:

read,

write,

admin

agent.mcp_config.server_urls

string<uri>[] | null

Required string length: 1 - 2083

agent.delegated_agents

DelegatedAgent · object[]

Hide child attributes

agent.delegated_agents.url

string

required

agent.delegated_agents.agent_card_url

string | null

agent.delegated_agents.name

string | null

agent.delegated_agents.capabilities

string[] | null

agent.white_box_config

WhiteBoxConfig · object

Source code access configuration for white box analysis.

Hide child attributes

agent.white_box_config.source_code

string | null

agent.white_box_config.repo_url

string | null

agent.white_box_config.github_username

string | null

agent.white_box_config.repo_branch

string | null

agent.white_box_config.entry_point

string | null

agent.agent_metadata

AgentMetadata · object

Agent metadata for display and organization.

Hide child attributes

agent.agent_metadata.role

string | null

agent.agent_metadata.job_description

string | null

agent.agent_metadata.version

string | null

agent.agent_metadata.author

string | null

agent.agent_metadata.tags

string[] | null

agent.purpose

string | null

agent.protocol

enum<string>

default:chat_completions

Communication protocol for agent endpoints.

Available options:

chat_completions,

a2a

agent.test_score

string | null

Pattern: ^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$

agent.last_tested_by

string | null

agent.evaluated_harnesses

string[] | null

agent.last_evaluated_at

integer | null

agent.protection_status

enum<string>

default:unprotected

Dome protection lifecycle state.

Available options:

unprotected,

configured,

domed

agent.trust_stage

enum<string>

default:registered

Trust maturity lifecycle stage for an agent.

Available options:

registered,

tested,

hardened,

trusted,

optimized,

adapted

agent.trusted_at

integer | null

agent.ttt_days

number | null

agent.dome_config_id

string<uuid> | null

agent.dome_manually_configured

boolean

default:false

agent.import_metadata

ImportMetadata · object

Metadata about how an agent was imported.

ImportMetadata
Import Metadata

Hide child attributes

agent.import_metadata.source

enum<string> | null

Import source for agent configuration.

Available options:

manual

agent.import_metadata.source_url

string | null

agent.import_metadata.imported_at

integer | null

agent.import_metadata.original_format

string | null

agent.capabilities

AgentCapabilities · object

Agent capability flags.

AgentCapabilities
Capabilities

Hide child attributes

agent.capabilities.streaming

boolean

default:false

agent.capabilities.push_notifications

boolean

default:false

agent.capabilities.code_execution

boolean

default:false

agent.capabilities.memory

boolean

default:false

agent.capabilities.delegation

boolean

default:false

agent.capabilities.tools

string[]

agent.skills

(AgentSkill · object | object)[]

An agent skill definition (for A2A protocol agents).

AgentSkill
Option 2

Hide child attributes

agent.skills.id

string

required

agent.skills.name

string

required

agent.skills.description

string | null

agent.skills.input_modes

string[]

agent.skills.output_modes

string[]

agent.latest_evaluation

AgentLatestEvaluation · object

Latest completed evaluation scores for an agent.

Sideloaded on GET /agent-configurations when include_scores=true. Contains only domain-level score data — no UI or presentation concerns.

Hide child attributes

agent.latest_evaluation.evaluation_id

string<uuid>

required

agent.latest_evaluation.overall_score

number | null

agent.latest_evaluation.reliability_score

number | null

agent.latest_evaluation.security_score

number | null

agent.latest_evaluation.safety_score

number | null

agent.latest_evaluation.completed_at

integer | null

access_level

string

required

warnings

string[]

external_id

string | null

identity_provider

string | null

Quick Start

Deploy Vijil

Agentic Workflow

Evaluate Agents

Protect Agents

API Reference

Import Agent Unified

Body

Response