Developer API

Integrate AutoPersonas into your own applications and workflows with our REST API — 180+ endpoints to manage influencers, generate content, publish posts, create videos, and read analytics, all programmatically. Building an AI agent instead? Use the hosted MCP server, which wraps this same API.

Authentication

Mint a key in Settings > API Keys (open it here). Keys look like ap_live_ followed by 64 hex characters, and the full key is shown exactly once at creation — only a SHA-256 hash is stored, so copy it immediately. Pass it as a Bearer token in the Authorization header of every request:

Authorization: Bearer ap_live_...

Keys are scoped — when creating a key, grant only the permissions it actually needs (see Scopes). You can revoke or rotate keys at any time from Settings; revocation takes effect immediately.

Generative endpoints additionally require billing setup (a payment method on file). Until then they return 403 with "error_code": "billing_required" and a remediation_url pointing at Settings > Billing.

Base URL

https://autopersonas.com/api/v1

Every successful response is wrapped in a data envelope: { "data": ... }. Errors return { "error": "message" } with a non-2xx status.

A quick way to verify a key: GET /api/v1/me requires no scope and returns your key's metadata, scopes, and current rate-limit state.

Rate Limits

• 60 requests per minute per API key (sliding window; the default — a key's limit can differ).
• Every response includes X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset (unix seconds) headers.
• Exceeding the limit returns 429 Too Many Requests. Back off and retry after the reset time.

Scopes

Each API key is assigned one or more scopes that determine what it can access. A request to an endpoint whose scope the key lacks returns 403.

Endpoints

The full endpoint reference below is generated from the same route map that powers the API, grouped by resource. For request/response schemas and live try-out, use the Swagger UI (the raw spec is at /api/openapi.json).

Some groups are gated: Flows endpoints are in beta and require a Pro or Agency plan, and a few endpoints sit behind feature flags that are off by default — calling them without access returns 403 or 404.

Error Codes

Code Examples

List Influencers

curl https://autopersonas.com/api/v1/influencers \
  -H "Authorization: Bearer ap_live_YOUR_KEY"

Generate Content

Requires content:generate. directionContext steers the batch; count is 1–5 items. The response returns a batchId — poll GET /api/v1/batches/:id until generation finishes.

curl -X POST https://autopersonas.com/api/v1/content/generate \
  -H "Authorization: Bearer ap_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "profileId": "prof_abc123",
    "count": 3,
    "directionContext": { "topic": "morning gym routine" }
  }'

Publish a Post

Requires publishing:write. Publishes an approved content item to the platforms connected to its profile.

curl -X POST https://autopersonas.com/api/v1/content/CONTENT_ID/publish \
  -H "Authorization: Bearer ap_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

Using an AI Agent?

If you are connecting an AI agent (Claude, ChatGPT, Cursor, or any MCP-compatible client) rather than writing HTTP calls yourself, use the hosted MCP server instead — one URL, no SDK, the same API keys and scopes.

Interactive Docs

Prefer to explore the API visually? Open the Swagger UI to browse every endpoint, try requests live, inspect response schemas, and copy ready-made code snippets.