Lakera Projects API
The projects API from Lakera — 2 operation(s) for projects.
The projects API from Lakera — 2 operation(s) for projects.
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/lakera:lakera-projects-api"
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
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: Platform Projects API
version: 1.0.0
servers:
- url: https://platform.lakera.ai/api
description: Platform
tags:
- name: Projects
paths:
/v1-beta/projects:
post:
operationId: projects_createProject
summary: Create project
description: Create a new project
tags:
- Projects
responses:
'200':
description: Project created
content:
application/json:
schema:
$ref: '#/components/schemas/Project'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/Project'
security:
- bearerAuth: []
/v1-beta/projects/{projectId}:
get:
operationId: projects_getProject
summary: Get project
description: Get a specific project by ID
tags:
- Projects
parameters:
- name: projectId
in: path
required: true
schema:
type: string
responses:
'200':
description: Project details
content:
application/json:
schema:
$ref: '#/components/schemas/Project'
security:
- bearerAuth: []
put:
operationId: projects_updateProject
summary: Update project
description: Update a specific project
tags:
- Projects
parameters:
- name: projectId
in: path
required: true
schema:
type: string
responses:
'200':
description: Project updated
content:
application/json:
schema:
$ref: '#/components/schemas/Project'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/Project'
security:
- bearerAuth: []
delete:
operationId: projects_deleteProject
summary: Delete project
description: Delete a specific project
tags:
- Projects
parameters:
- name: projectId
in: path
required: true
schema:
type: string
responses:
'200':
description: Project deleted
content:
application/json:
schema:
$ref: '#/components/schemas/Projects_deleteProject_Response_200'
security:
- bearerAuth: []
components:
schemas:
ProjectAction:
type: string
enum:
- detect
- enforce
description: 'Controls whether Guard enforces flagging on this project. `enforce` (the default) means full enforcement: the top-level `flagged` in a `guard` response is `true` whenever any of the enabled detectors triggers. `detect` surfaces detections in the breakdown but forces the top-level `flagged` to `false`, letting you observe detector behavior without blocking traffic. Always returned when reading a project. Optional when creating — defaults to `enforce`. Optional when updating — omit to keep the existing value. More information in [Project Mode](/docs/projects#project-mode).
'
title: ProjectAction
Project:
type: object
properties:
name:
type: string
description: A descriptive name for the project
policy_id:
type: string
description: ID of the policy to be applied to this project. If not provided, uses default policy.
project_metadata:
type: object
additionalProperties:
type: string
description: Custom metadata tags for analysis and cross referencing
action:
$ref: '#/components/schemas/ProjectAction'
description: 'Controls whether Guard enforces flagging on this project. `enforce` (the default) means full enforcement: the top-level `flagged` in a `guard` response is `true` whenever any of the enabled detectors triggers. `detect` surfaces detections in the breakdown but forces the top-level `flagged` to `false`, letting you observe detector behavior without blocking traffic. Always returned when reading a project. Optional when creating — defaults to `enforce`. Optional when updating — omit to keep the existing value. More information in [Project Mode](/docs/projects#project-mode).
'
required:
- name
description: Project configuration for organizing policies and API keys
title: Project
Projects_deleteProject_Response_200:
type: object
properties: {}
description: Empty response body
title: Projects_deleteProject_Response_200
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: "Bearer authentication using API key. Generate an API key from the AI Guardrails Dashboard.\nExample: Bearer sk_123...\n\nKeys carry one of two access scopes, chosen when the key is created:\n\n- **Read and write** — may call every endpoint. This is the default, and the\n scope of every key created before scopes were introduced.\n- **Read only** — may call read endpoints such as `/v1-beta/logs`,\n `/v1-beta/analytics` and the `GET` endpoints. Write endpoints return `403`.\n\nIssue a read-only key to anything that only needs to retrieve data, such as a\nlog-shipping job or a dashboard, so that it cannot modify your policies or\nprojects.\n"
x-provenance:
method: harvested
publisher: Lakera
source: https://docs.lakera.ai/openapi/platform-api.yaml
note: split by refine-openapis from the provider's own published document, verified by fetch (openapi/_original/*.fetch.json);
stamped by stamp-openapi-provenance.py (roadmap#793)