# LLMentions > Measure how ChatGPT, Google AI Mode, Gemini, Claude, Perplexity, Grok, DeepSeek and Qwen mention and cite your brand. Agent-first: MCP, CLI and REST, with confidence intervals on every number. LLMentions is an API, MCP server and CLI for measuring brand visibility in AI answer engines. Every capability is an MCP tool, a CLI command and a REST endpoint. Responses use the envelope {data, meta: {charged_usd, balance_usd}} and errors carry a "hint" with the next step. Get a free test key (mock engines, never charged): POST https://api.llmentions.com/v1/signup {"name": "…"}. - MCP (streamable HTTP): https://api.llmentions.com/mcp with header "Authorization: Bearer sk_…" - OpenAPI: https://api.llmentions.com/openapi.json - Prices (USD; credits are dollars): https://llmentions.com/pricing.json ## Docs - [Quickstart](https://llmentions.com/docs/index.md): Get a free test key, ask your first question across AI answer engines, and connect an agent over MCP in under two minutes. - [MCP](https://llmentions.com/docs/mcp.md): Connect Claude Code, Claude Desktop, Cursor, or any MCP client to LLMentions over streamable HTTP, and the full tool catalog. - [CLI](https://llmentions.com/docs/cli.md): The llmentions command-line tool — every command maps 1:1 to a REST endpoint and an MCP tool. - [REST API](https://llmentions.com/docs/api.md): Authentication, the response envelope, agent-actionable errors, endpoints, and signed webhooks for the LLMentions REST API. - [Billing](https://llmentions.com/docs/billing.md): Credits are dollars. Per-answer prices, quotes, holds and refunds, free test keys, and what is always free. - [Methodology](https://llmentions.com/docs/methodology.md): Why every LLMentions number is a sampled proportion with a 95% confidence interval, how sources are labelled, and how changes are tested. ## Optional - [Full docs in one file](https://llmentions.com/llms-full.txt) - [Pricing](https://llmentions.com/pricing/)