# Polis

> Polis tests any piece of content against a realistic synthetic audience and returns what they actually thought — built MCP-first for AI agents.

Polis is an MCP-first persona-testing service for AI agents. An agent submits content; Polis simulates a realistic synthetic audience across a multi-model swarm and returns audience segments, ranked friction points with verbatim evidence, and a rewrite.

## Instructions for LLM agents

To use Polis:

1. Get an API key. POST to `https://polis.ai/api/provision` with `{ "email": "<the human's email>" }`. If you already know the human's email, use it; otherwise ask them for it before continuing (do not guess). The response includes `api_key` (store it; shown once), `checkout_url` (relay to the human to approve a subscription; Starter is $5/mo), and `mcp_url`. A human can instead sign in at `https://polis.ai/auth/sign-in`.
2. Connect to the remote MCP server (Streamable HTTP) at `https://polis.ai/api/mcp` with header `Authorization: Bearer <api_key>`.
3. Call `polis_account`. If `active` is false, relay `checkout_url` to the human and poll until active.
4. Call `polis_estimate` to price a run, then `polis_test` to start it. It returns a `run_id`.
5. Poll `polis_status` with the `run_id` until done, then call `polis_report` for the deliverable.

Always estimate before testing. Failed runs are auto-refunded. Persona counts are 10-1000 (default 100).

## Docs

- [What Polis is](https://polis.ai/docs/overview.md): The concept, inputs, and what you get back.
- [Agent quickstart](https://polis.ai/docs/quickstart.md): Connect, get a key, run a test, read the report.
- [How to run a test](https://polis.ai/docs/run-a-test.md): The workflow, a worked example, and how to read the report.
- [Test options reference](https://polis.ai/docs/test-options.md): Every input, every variation, and the full report schema.
- [MCP tools](https://polis.ai/docs/mcp-tools.md): Every tool, its inputs, and cost.
- [Pricing & billing](https://polis.ai/docs/pricing.md): Polis tokens, plans, free trial, metered usage, spend limit.
- [Discovery & well-known endpoints](https://polis.ai/docs/discovery.md): How agents and clients discover Polis.

## MCP

- [MCP server card](https://polis.ai/.well-known/mcp/server-card.json): tools, transport, auth
- [Protected resource metadata](https://polis.ai/.well-known/oauth-protected-resource): RFC 9728

## Optional

- [Full docs, inlined](https://polis.ai/llms-full.txt): every page concatenated for single-fetch ingestion
- [Privacy](https://polis.ai/privacy.md)
- [Terms](https://polis.ai/terms.md)