Aetherya — Agent Portal
This page is the agent-native interface for Aetherya. Content is identical for humans and agents — no cloaking. Markdown version: /agent.md.
Identity
Aetherya is a synthetic-audience behavioral-simulation platform. It generates statistically grounded personas and runs them through your site, copy, or product to predict real-audience outcomes — predicted friction, hesitation, drop-off, and messaging clarity — before launch, at agent speed.
Category: synthetic user research an agent can loop on in minutes.
Full platform overview: /platform.md
Directory
A curated map of every agent-readable surface on this site.
Act
MCP (recommended for agent clients)
Install via the published npm package:
# Add to Claude Code
claude mcp add aetherya -- npx -y @aetherya/mcp
npx -y @aetherya/mcp authFor Claude Desktop / Cursor / Windsurf / VS Code, see /mcp.md.
API (direct HTTP)
Base URL: https://api.aetherya.ai/api
Agent access tokens are short-lived and workspace-bound:
Authorization: Bearer <short-lived-agent-token>Legacy aeth_live_ API keys remain supported for existing integrations and may require x-aetherya-workspace-id.
Rate limits: 60 requests/minute. Monthly session cap per plan.
429— rate limit exceeded;Retry-Afterheader present.402— monthly session cap reached; top up or upgrade.
Async audit pattern:
POST /api/audits/run → { job_id, status: "queued" }
GET /api/audits/jobs/:id → { status: "running"|"completed"|"failed" }
GET /api/audits/:id?view=agent → normalised findings JSONFull schema: /openapi.json
Credentials
Agents should use discovery-first delegated authentication from /auth.md. Legacy API keys (aeth_live_) remain available from Settings → API Keys.
The service-auth flow opens a human claim ceremony. The user reviews the exact workspace and capabilities, then confirms the six-digit code. No key copy/paste is required:
- Human creates an Aetherya account at /signup
- Agent discovers metadata and opens the verification URL
- Human confirms the request at /claim
Delegations are bound to one workspace and can be revoked from Settings → API & agent access.
Billing
Checkout and billing changes require a human in the Aetherya dashboard. Agent purchase-intent endpoints are not currently advertised or available.
Pricing: /pricing.md | /api/public/pricing
Rules
Agent access is governed by the Agent Access Policy (forthcoming — legal review in progress).
Key rules (preview):
- Agents must self-identify (UA or client name). Disguised automation = unauthorized access.
- Sanctioned surfaces: public pages,
/agent, documented APIs (/openapi.json), MCP. Browser automation against/dashboardis unsupported. - All agent actions execute under a delegating human account; that human is responsible.
- High-impact actions (purchases, key minting) require human approval.
- Data retrieved from Aetherya may be used as inference-time input; bulk retrieval for model training is prohibited.
Status
{
"apiBaseUrl": "https://api.aetherya.ai/api",
"mcpTransport": "stdio",
"mcpPackage": "@aetherya/mcp",
"protocolVersions": {
"mcp": "2025-11-05",
"openapi": "3.1.0"
},
"agentPolicyStatus": "active-preview",
"delegatedOnboarding": "service_auth+anonymous",
"remoteMcpEndpoint": "roadmap"
}