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

# Choose an integration

> Pick between the MCP server, the Playwright SDK and the agent skill in under a minute.

Pick how your agent connects to Agent Vault in under a minute, then go to its
setup page.

| Option | Choose it if | You write | Set up |
| - | - | - | - |
| **MCP server** | Your agent runs in an MCP host such as Claude Code, Claude Desktop, Codex or Cursor. Right for most people | A line to paste (hosted) or a config block (self-run). The dashboard generates both | [MCP setup](/mcp/setup) |
| **Playwright SDK** | You write the agent yourself in TypeScript and want full browser control | TypeScript | [Install the SDK](/sdk/install) |
| **Agent skill** | You want your agent to follow the rules without a long system prompt. Use it with one of the other two | Nothing, you install a file | [Rules of engagement](/mcp/rules-of-engagement#install-the-skill) |

If you are unsure, start with the MCP server. The dashboard's **Overview** page
generates the finished setup. Where your deployment runs a hosted MCP server,
OpenClaw, Claude Code, Hermes and Codex each have a **Sign in** route, a line to
paste with no API key, and a **Use an API key** route, the self-run block with
your key filled in. Meta Muse, Grok Bot, Claude Desktop and Antigravity only
sign in, and Claude Desktop is added in its settings rather than with a pasted
line. For the agents with their own setup page, see
[Connect your agent](/agents/overview).

## MCP server

`@agentvault/mcp` gives your agent 29 tools, such as `get_token_catalog`,
`fill_checkout` and `request_challenge_handoff`. It drives one page at a time,
reused across calls, which suits conversational agents and one-off errands. You
connect it in one of two ways:

* **Hosted**, where your deployment runs one: your host adds a remote server
  and you sign in with your Agent Vault account. There is no API key and nothing
  to install.
* **Self-run**: your host launches the server as a local stdio process, with
  your API key in its environment.

See [MCP setup](/mcp/setup) and the [tool reference](/mcp/tool-reference).

## Playwright SDK

`@agentvault/playwright` is a Playwright-shaped browser object model that talks
to the proxy over a WebSocket. You get full contexts, pages, popups and frame
locators, plus your own retry logic, which suits scripted runs and batch jobs.
It runs on Bun, or Node 20 or later. See [Install the SDK](/sdk/install).

## Agent skill

The skill is a file, not a client. It teaches an agent to use only mock tokens,
never invent a password, fill card fields in the right order, and hand challenges
to you. A companion [checkout recipes skill](/registry/skill) teaches it to look
up a store in the registry first.

## What every option shares

**The same protections.** The rules belong to the token, so a fill through
`fill_checkout` is checked exactly like one through `page.fill()`, whichever way
your agent connects.

## What you need

The SDK and the self-run MCP server need:

* **An API key** from the dashboard's **API keys** page. See
  [API keys](/dashboard/api-keys).
* **The same three environment variables.** See
  [Environment variables](/reference/environment-variables).
* **No npm install.** Both packages are tarballs that Agent Vault hosts. See
  [Install the SDK](/sdk/install#the-install-url).

The hosted MCP server needs none of these. It needs:

* **An MCP client that supports remote servers over streamable HTTP with
  OAuth.** You sign in with your Agent Vault account, and the
  client keeps the token.
* **Access chosen on Connected apps.** A new connection can use nothing until
  you click **Choose access** on its row on **Connected apps** and then
  **Save access**. See [Connect to the hosted server](/mcp/setup#connect-to-the-hosted-server).

<Accordion title="Can I use the HTTP API directly?">
  Partly. An agent in any language can read its token catalog and the recipe
  registry over HTTP. Filling fields goes through the proxy's WebSocket protocol,
  and the MCP server and the SDK are its two supported clients. See
  [HTTP API](/reference/http-api).
</Accordion>

**Next:** [MCP setup](/mcp/setup) to add Agent Vault to your MCP host.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.