---
name: character-ai
description: Operate Character.AI as an agent using public APIs, CLIs, and docs. Twin Score agent 35.
---

# Character.AI skill

Character.AI popularized persona chat: millions of user-created characters for entertainment, language practice, and roleplay. It is a human consumer product. There is no serious public API for agents to operate characters as tools, and the company has invested in safety and under-18 protections rather than developer platforms. Agent Twin Score is low on purpose — this is not a gap we paper over with a fake MCP listing. Twin Score on this directory is 72 for humans and 35 for agents, using the public rubric (interface, onboarding, human docs, collaboration, support, pricing fairness, accessibility, reliability versus API quality, MCP or tool surface, CLI, structured docs, machine auth, quotas, determinism, and skill packaging). Character.AI is sold by Character.AI, founded 2021, headquartered in Menlo Park, USA. Pricing in public materials: Free with cAI+ subscription for faster responses and features. Machine capabilities we record: API none, MCP none, CLI none, docs basic, auth Account only. This page is editorial, not a star rating scraped from users.

## When to use

Use this skill when a user asks to integrate, script, or evaluate Character.AI (Character.AI).

## When not to use

Do not claim an MCP server exists unless the capability matrix says so (current MCP level: none). Do not invent user-count ratings.

## Capability matrix

| Surface | Level |
|---|---|
| API | none |
| MCP | none |
| CLI | none |
| Docs | basic |
| Auth | Account only |
| Webhooks | basic |
| SDKs | none listed |

## Auth

Account only

## Pricing (public)

Free with cAI+ subscription for faster responses and features.

## Official site

https://character.ai

## Twin Score

Human 72. Agent 35. Updated 2026-08-01. Rubric: https://buildsomethingagentswant.com/scorecard

## Alternatives

- chatgpt
- claude