# anysite-mcp

[![npm](https://img.shields.io/npm/v/anysite-mcp)](https://www.npmjs.com/package/anysite-mcp)
[![license](https://img.shields.io/github/license/DwytMCL/anysite-mcp)](LICENSE)
[![MCP](https://img.shields.io/badge/MCP-server-blue)](https://modelcontextprotocol.io)

**Turn any website into tools for Claude and other AI agents, signed in as you.**

![Claude looks something up on Wikipedia, saves the steps as a shortcut, and reuses it as a new tool](docs/demo.gif)

```bash
claude mcp add anysite -- npx -y anysite-mcp
```

anysite-mcp is an [MCP](https://modelcontextprotocol.io) server that drives a real Chrome on your computer. Every
site gets its own browser profile that you sign in to once, by hand. The agent then works the site the way a
screen reader does, by role and name, so small redesigns don't break it. When the agent gets a job done, it can save
the steps as a **shortcut**, and that shortcut becomes a new tool it can call in one step next time.

No API keys, no cloud browser, no extra LLM. Your logins stay on your machine.

- **Your accounts, kept apart.** One Chrome profile per site, signed in by hand once. Works with Google sign-in.
- **Gets faster with use.** The agent turns a job it has figured out into a one-call tool that's there next session.
- **Survives redesigns.** Elements are found by role and name, not CSS selectors.
- **Packs for popular sites.** Gemini and NotebookLM are included; a new pack is one file.

```text
You:    Ask Gemini to summarise this PDF, then add the summary as a source to my "Thesis" notebook in NotebookLM.

Claude: gemini_ask { prompt: "Summarise this PDF in 10 bullet points", files: ["~/Downloads/paper.pdf"] }
        → - The study compares …   (Chat: https://gemini.google.com/app/…)
        notebooklm_add_source { notebook: "Thesis", text: "- The study compares …" }
        → Added pasted text.

You:    Check my GitHub notifications.

Claude: web_open { site: "github.com", url: "/notifications" }
        → This looks like a sign-in page. Call web_login for "github.com" …
        web_login { site: "github.com" }
        "A Chrome window opened on GitHub. Sign in there, then quit that window and tell me."
You:    done
Claude: web_open { site: "github.com", url: "/notifications" }   → (accessibility tree of your inbox)
        web_save_shortcut { site: "github.com", name: "notifications",
          description: "List unread GitHub notifications",
          steps: [{ "action": "open", "url": "/notifications" }, { "action": "read", "role": "main" }] }
        → Saved github_com_notifications.

(Next week, in a new session)
You:    Anything new on GitHub?
Claude: github_com_notifications {}   → 3 unread: …
```

## Why another browser MCP?

| | anysite-mcp | Playwright MCP | browser-use / Stagehand |
|---|---|---|---|
| Signed in as you | Yes, a separate profile per site, signed in by hand once | One profile for everything, or a fresh one each run | Usually cloud or fresh browsers |
| Google sign-in (Gemini, NotebookLM, Gmail) | Works: sign-in happens in a plain, non-automated window | Often refused as an "insecure browser" | Often refused |
| Gets faster with use | The agent saves working steps as new tools | No | No |
| Site packs | NotebookLM and Gemini included; add your own in one file | No | No |
| Needs an LLM API key | No | No | Yes |

Profiles are kept apart on purpose. Copying a signed-in profile so two browsers share one session gets that
session revoked by Google (and other careful sites), which logs you out everywhere.

## Install

You need Node 18+ and Chrome (or `npx playwright install chromium`).

1. Sign in to the sites you want, once each. A normal Chrome window opens; sign in, then quit it (Cmd+Q on a Mac).

   ```bash
   npx -y anysite-mcp login gemini
   npx -y anysite-mcp login notebooklm
   npx -y anysite-mcp login github.com
   ```

2. Add the server to your agent.

   Claude Code:

   ```bash
   claude mcp add anysite -- npx -y anysite-mcp
   ```

   Claude Desktop, Cursor and others (`claude_desktop_config.json` or the client's MCP settings):

   ```json
   { "mcpServers": { "anysite": { "command": "npx", "args": ["-y", "anysite-mcp"] } } }
   ```

With no arguments the server offers every site you have signed in to. To pick sites, list them:
`npx -y anysite-mcp gemini github.com`. The agent can also add a new site at any time by calling `web_login`.

## Tools

**Any site** (each takes `site`: a pack name like `gemini`, or a domain like `github.com`):

| Tool | What it does |
|---|---|
| `web_snapshot` | The page's accessibility tree: roles, names and text. Give `role`/`name` to see only part of it. |
| `web_open` | Go to a URL (absolute or relative to the site) |
| `web_click`, `web_type`, `web_press` | Act on an element found by role and name, or by visible text (add `within: "dialog"` and so on to look only inside one part of the page) |
| `web_read` | Text of the page or of one element |
| `web_wait` | Wait, or wait until some text appears |
| `web_upload`, `web_download` | Give files to a file picker; save a download |
| `web_screenshot` | PNG of the page, for when the tree is not enough |
| `web_login` | Open a plain window so you can sign in |
| `web_save_shortcut`, `web_delete_shortcut` | Turn a working sequence into a tool named `<site>_<name>` |

**Packs included**

- `gemini`: `gemini_ask` (prompt, files, model, tools such as Create image or Deep Research; returns the reply as markdown), `gemini_list_chats`
- `notebooklm`: `notebooklm_ask`, `notebooklm_add_source` (URLs, text, files), `notebooklm_create_notebook`, `notebooklm_list_notebooks`

## Shortcuts

A shortcut is a list of steps, each one the arguments of a `web_*` tool plus its `action`. `{{param}}` is
filled in from the tool's arguments. It returns the text of its `read` steps. Shortcuts are saved in
`~/.anysite-mcp/sites/<site>.json`, which you can edit, share or commit:

```json
{
  "search": {
    "description": "Search Hacker News and return the results",
    "params": { "query": "What to search for" },
    "steps": [
      { "action": "open", "url": "https://hn.algolia.com/?q={{query}}" },
      { "action": "wait", "seconds": 5, "until_text": "results" },
      { "action": "read", "role": "main" }
    ]
  }
}
```

If a site changes and a step fails, the error says which step, and the agent can redo the job with the `web_*`
tools and save the shortcut again.

## Write a pack

For logic that steps can't express (waiting for a streamed answer, parsing a list), write a pack: a file in
`~/.anysite-mcp/sites/<name>.js`. It needs no dependencies; `z` (zod) and some helpers are passed in. The bundled
[`sites/gemini.js`](sites/gemini.js) and [`sites/notebooklm.js`](sites/notebooklm.js) are full examples.

```js
export default ({ z, kit }) => ({
  url: 'https://news.ycombinator.com/',
  tools: {
    top: {
      description: 'Titles and links of the Hacker News front page',
      input: { limit: z.number().optional() },
      run: async (page, { limit = 10 }) => {
        await page.goto('https://news.ycombinator.com/');
        const links = await page.locator('.titleline > a').evaluateAll(as => as.map(a => `${a.innerText}\t${a.href}`));
        return links.slice(0, limit).join('\n');
      },
    },
  },
});
```

Then run `npx -y anysite-mcp login hn` (or just use `site: "hn"`), and the agent gets `hn_top`. A pack in
`~/.anysite-mcp/sites` with the same name as a bundled one replaces it. Pull requests with new packs are welcome.

## How it works

- Each site's Chrome runs with its own `--user-data-dir` in `~/.anysite-mcp/profiles/<site>` and a debugging port
  it picks itself. The server reconnects to it if it is still open, so tabs survive restarts.
- Sign-in uses a plain Chrome with no debugging port, because Google and others block sign-in in automated browsers.
- Elements are found with Playwright's role, label and text locators, never CSS selectors. When a click is
  blocked by an overlay, the element is operated from the keyboard instead.

Settings (environment variables): `ANYSITE_HOME` (default `~/.anysite-mcp`), `ANYSITE_CHROME` (browser binary),
`ANYSITE_DOWNLOADS` (default `~/Downloads/anysite`).

## Safety

The agent acts as you on the sites you sign in to. Only sign in to sites you are happy for it to use, and keep an
eye on anything that sends, buys or deletes. Profiles hold your cookies: never share or commit
`~/.anysite-mcp/profiles`.

## Development

```bash
npm install
npm test   # starts the server on example.com, saves and runs a shortcut
```

MIT License.