Mabl Agent Instruction API
The AgentInstruction API from Mabl — 2 operation(s) for agentinstruction.
The AgentInstruction API from Mabl — 2 operation(s) for agentinstruction.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.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.curl "https://apis.io/api/v1/apis/mabl:mabl-agentinstruction-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a 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. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: mabl Agent Instruction API
description: APIs for interacting with mabl services
version: 0.599.3.1792436330
x-readme-id: 62c896636916ce01d2ff4f5a
servers:
- url: /
security:
- basicAuth: []
- bearerAuth: []
tags:
- name: AgentInstruction
paths:
/agentInstruction:
get:
tags:
- AgentInstruction
summary: Query agent instructions
description: Query agent instructions for a workspace with optional filters
operationId: queryAgentInstructions
parameters:
- name: workspace_id
in: query
description: The ID of the workspace to query instructions for
required: true
style: form
explode: true
schema:
type: string
- name: capability
in: query
description: Filter by capability (returns instructions that include this capability)
required: false
style: form
explode: true
schema:
$ref: '#/components/schemas/AgentInstructionCapability'
- name: application_id
in: query
description: Filter by application ID (returns instructions that include this application)
required: false
style: form
explode: true
schema:
type: string
- name: environment_id
in: query
description: Filter by environment ID (returns instructions that include this environment)
required: false
style: form
explode: true
schema:
type: string
- name: test_type
in: query
description: Filter by test type (returns instructions that include this test type)
required: false
style: form
explode: true
schema:
$ref: '#/components/schemas/TestTypeEnum'
- name: limit
in: query
description: Maximum number of results to return
required: false
style: form
explode: true
schema:
type: integer
format: int32
- name: cursor
in: query
description: Pagination cursor from a previous query result
required: false
style: form
explode: true
schema:
type: string
responses:
'200':
description: The query results
content:
application/json:
schema:
$ref: '#/components/schemas/AgentInstructionQueryResult'
'400':
$ref: '#/components/responses/ErrorResponse400'
'401':
$ref: '#/components/responses/ErrorResponse401'
'403':
$ref: '#/components/responses/ErrorResponse403'
default:
$ref: '#/components/responses/ErrorResponse'
x-mabl-action: Read::AgentInstruction
post:
tags:
- AgentInstruction
summary: Create a new agent instruction
description: Creates a new agent instruction for a workspace
operationId: createAgentInstruction
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateAgentInstructionRequest'
required: true
responses:
'201':
description: The created agent instruction
content:
application/json:
schema:
$ref: '#/components/schemas/AgentInstruction'
'400':
$ref: '#/components/responses/ErrorResponse400'
'401':
$ref: '#/components/responses/ErrorResponse401'
'403':
$ref: '#/components/responses/ErrorResponse403'
default:
$ref: '#/components/responses/ErrorResponse'
x-mabl-action: Create::AgentInstruction
/agentInstruction/{instruction_id}:
get:
tags:
- AgentInstruction
summary: Get an agent instruction
description: Retrieves a specific agent instruction by ID
operationId: getAgentInstruction
parameters:
- name: instruction_id
in: path
description: The ID of the agent instruction
required: true
style: simple
explode: false
schema:
type: string
responses:
'200':
description: The agent instruction
content:
application/json:
schema:
$ref: '#/components/schemas/AgentInstruction'
'401':
$ref: '#/components/responses/ErrorResponse401'
'403':
$ref: '#/components/responses/ErrorResponse403'
'404':
$ref: '#/components/responses/ErrorResponse404'
default:
$ref: '#/components/responses/ErrorResponse'
x-mabl-action: Read::AgentInstruction
delete:
tags:
- AgentInstruction
summary: Delete an agent instruction
description: Deletes an agent instruction
operationId: removeAgentInstruction
parameters:
- name: instruction_id
in: path
description: The ID of the agent instruction to delete
required: true
style: simple
explode: false
schema:
type: string
responses:
'204':
description: Successfully deleted
'401':
$ref: '#/components/responses/ErrorResponse401'
'403':
$ref: '#/components/responses/ErrorResponse403'
'404':
$ref: '#/components/responses/ErrorResponse404'
default:
$ref: '#/components/responses/ErrorResponse'
x-mabl-action: Delete::AgentInstruction
patch:
tags:
- AgentInstruction
summary: Update an agent instruction
description: Updates an existing agent instruction
operationId: updateAgentInstruction
parameters:
- name: instruction_id
in: path
description: The ID of the agent instruction to update
required: true
style: simple
explode: false
schema:
type: string
- name: If-Match
in: header
description: ETag for optimistic locking
required: false
style: simple
explode: false
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/AgentInstruction'
required: true
responses:
'200':
description: The updated agent instruction
content:
application/json:
schema:
$ref: '#/components/schemas/AgentInstruction'
'400':
$ref: '#/components/responses/ErrorResponse400'
'401':
$ref: '#/components/responses/ErrorResponse401'
'403':
$ref: '#/components/responses/ErrorResponse403'
'404':
$ref: '#/components/responses/ErrorResponse404'
default:
$ref: '#/components/responses/ErrorResponse'
x-mabl-action: Edit::AgentInstruction
components:
responses:
ErrorResponse401:
description: User not authenticated
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponseGeneric'
ErrorResponse404:
description: Entity not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponseGeneric'
ErrorResponse400:
description: Invalid or missing parameter
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponseGeneric'
ErrorResponse403:
description: User not authorized
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponseGeneric'
ErrorResponse:
description: Unknown error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponseGeneric'
schemas:
AgentInstructionCapability:
type: string
description: Capability that an agent instruction applies to
enum:
- authoring
- recovery
- results_analysis
- repair_notes
TestTypeEnum:
type: string
description: Type of test
enum:
- api
- browser
- performance
- mobile
- desktop
x-mabl-scope: public
GuardrailApprovalKind:
type: string
description: Who decides a guardrail approval. SELF is decided by the person the agent acts for; WORKSPACE, for an agent acting for an API key, by a workspace owner or editor.
enum:
- SELF
- WORKSPACE
GuardrailRefusal:
type: object
properties:
id:
type: string
description: The id of the guardrail policy that decided the refusal.
reason:
type: string
description: Why the policy refuses the request, written for the person the agent acts for.
decision_id:
type: string
description: The id of this decision in the guardrail decision log.
action:
type: string
description: The action the request was evaluated as, written Verb::Resource (for example Delete::Test), as declared by the operation's x-mabl-action extension.
policy_source:
type: string
description: 'Who set the deciding policy: workspace for a rule the workspace''s owners wrote, account for a rule set for the workspace''s account, mabl_agent_type for the agent type''s ceiling, and mabl_default for mabl''s own defaults.'
approval:
description: The approval for this request; present when error_code is approval_required and the approval could be recorded. Without it the request cannot be approved.
allOf:
- $ref: '#/components/schemas/GuardrailApprovalRef'
description: The guardrail policy that refused an agent request.
GuardrailApprovalState:
type: string
description: Where a guardrail approval stands. PENDING awaits a decision and expires undecided after 24 hours; APPROVED lets the agent repeat the request, as often as it does, for 20 minutes; DENIED refuses the same request for 20 minutes after the decision, after which asking again opens a new approval; CANCELLED means a person withdrew it while pending or revoked it while approved. EXPIRED and CANCELLED are final.
enum:
- PENDING
- APPROVED
- DENIED
- EXPIRED
- CANCELLED
GuardrailApprovalRef:
type: object
properties:
id:
type: string
description: The approval's id.
state:
description: Where the approval stands.
allOf:
- $ref: '#/components/schemas/GuardrailApprovalState'
kind:
description: Who decides the approval.
allOf:
- $ref: '#/components/schemas/GuardrailApprovalKind'
request_expires_time:
type: integer
description: When the approval expires if nobody decides it, in epoch milliseconds.
format: int64
url:
type: string
description: The mabl app page where a person reviews the approval.
description: 'An approval a guardrail policy asks for. While it is PENDING, stop: give the person the url, tell them the request is waiting for approval, and do not repeat the request or poll in a loop. Once a person tells you it is APPROVED, repeat the identical request with the header X-Mabl-Approval set to id. DENIED means a person said no, so do not work around it.'
CreateAgentInstructionRequest:
required:
- instruction_text
- name
- workspace_id
type: object
properties:
workspace_id:
type: string
description: The workspace to create the instruction in
name:
type: string
description: A short name or title for the instruction
instruction_text:
type: string
description: The instruction itself (plain text)
disabled:
type: boolean
description: Whether the instruction is disabled
capabilities:
type: array
description: Capabilities this instruction applies to
items:
$ref: '#/components/schemas/AgentInstructionCapability'
test_types:
type: array
description: Test types this instruction applies to
items:
$ref: '#/components/schemas/TestTypeEnum'
environment_ids:
type: array
description: Environment IDs this instruction applies to
items:
type: string
application_ids:
type: array
description: Application IDs this instruction applies to
items:
type: string
description: Request body for creating a new agent instruction
AgentInstruction:
type: object
properties:
instruction_id:
type: string
description: Unique identifier for the instruction
workspace_id:
type: string
description: The workspace this instruction belongs to
name:
type: string
description: A short name or title for the instruction
instruction_text:
type: string
description: The instruction itself (plain text)
x-dao-unindexed: true
disabled:
type: boolean
description: Whether the instruction is disabled. Disabled instructions are not injected into agent prompts.
capabilities:
type: array
description: Capabilities this instruction applies to
items:
$ref: '#/components/schemas/AgentInstructionCapability'
test_types:
type: array
description: Test types this instruction applies to
items:
$ref: '#/components/schemas/TestTypeEnum'
environment_ids:
type: array
description: Environment IDs this instruction applies to
items:
type: string
application_ids:
type: array
description: Application IDs this instruction applies to
items:
type: string
created_by_id:
type: string
description: The user who created this instruction
created_time:
type: integer
description: Creation timestamp in epoch milliseconds
format: int64
last_updated_by_id:
type: string
description: The user who last updated this instruction
last_updated_time:
type: integer
description: Last update timestamp in epoch milliseconds
format: int64
description: A user-defined instruction that tailors agent behavior for a workspace
x-implements-interface:
- HasWorkspaceId
- HasCreatedActivity
- HasUpdatedActivity
ErrorResponseGeneric:
type: object
properties:
id:
type: string
x-mabl-scope: public
code:
maximum: 599
minimum: 100
type: integer
format: int32
x-mabl-scope: public
message:
type: string
x-mabl-scope: public
error_code:
type: string
description: Machine-readable reason for the error, present only when the API names one. Values are guardrail_blocked (a guardrail policy refused an agent request), approval_required (a guardrail policy requires a person to approve the request first).
guardrail:
description: The guardrail policy that refused the request; present only when error_code is guardrail_blocked or approval_required.
allOf:
- $ref: '#/components/schemas/GuardrailRefusal'
AgentInstructionQueryResult:
type: object
properties:
agent_instructions:
type: array
items:
$ref: '#/components/schemas/AgentInstruction'
cursor:
type: string
description: Cursor for fetching the next page of results
description: Paginated query result for agent instructions
securitySchemes:
basicAuth:
type: http
scheme: basic
bearerAuth:
type: apiKey
name: Authorization
in: header