> ## Documentation Index
> Fetch the complete documentation index at: https://charlotte.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Charlotte MCP server: the web, readable for AI agents

> Charlotte is an MCP server that gives AI agents structured, token-efficient web access. Get a one-command claude.ai connector running in about a minute.

Charlotte is an MCP server that gives AI agents structured, token-efficient access to the web.
Instead of dumping the full accessibility tree on every call, Charlotte returns only what
the agent needs: a compact page summary on arrival, targeted queries for specific elements,
and full detail only when explicitly requested. On content-heavy pages that orientation is
up to \~140x smaller than a full accessibility-tree snapshot from [Playwright MCP](https://github.com/microsoft/playwright-mcp); on trivially small pages the two are roughly the same size.

## Try it in one command

Run Charlotte as a remote MCP server and connect it to claude.ai — no domain, no config:

```bash theme={null}
docker run --cap-add SYS_ADMIN --shm-size 2g -p 3737:3737 ghcr.io/ticktockbent/charlotte
```

It prints a public connector URL and an operator token. In claude.ai:
**Settings → Connectors → Add custom connector** — paste the URL, leave the
OAuth Client ID/Secret fields blank, and enter the token on Charlotte's consent
page when it appears. That's it; you're browsing.

<Note>
  The demo URL and token are ephemeral — both rotate on restart. For a stable
  domain, your own tunnel or reverse proxy, and docker compose, see
  [Self-Hosting](https://charlotte.mintlify.site/self-hosting).
</Note>

Prefer the stdio transport for a local MCP client (Claude Code, Claude Desktop, Cursor, and others)?

```bash theme={null}
npm install -g @ticktockbent/charlotte
```

Full client configuration and CLI usage live in the [project README](https://github.com/TickTockBent/charlotte#readme).

## Where to go next

* **[Self-Hosting](https://charlotte.mintlify.site/self-hosting)** — stand up Charlotte Remote on your own host: token, config, compose, and connecting claude.ai.
* **[Security](https://charlotte.mintlify.site/security)** — the trust boundary, SSRF and Host-header guards, the OAuth handshake, and sizing.
* **[Docker](https://charlotte.mintlify.site/docker)** — image choices, sandbox posture, and running the container in production.
* **[Configuration](https://charlotte.mintlify.site/configuration)** — every config key, environment variable, and precedence rule.
* **[Benchmarks](https://charlotte.mintlify.site/benchmarks)** — Charlotte vs. Playwright MCP, measured: orientation cost, per-task cost, and where Charlotte still loses.
* **[Changelog](https://charlotte.mintlify.site/changelog)** — release history and what's new.


## Related topics

- [Charlotte vs. Playwright MCP benchmarks](/benchmarks.md)
- [Charlotte Remote security model and network guards](/security.md)
- [Configuration](/configuration.md)
- [Charlotte changelog and release notes](/changelog.md)
- [Self-host Charlotte Remote and connect to claude.ai](/self-hosting.md)