# Scalebrowser (npm · @scalebrowser/mcp)

Isolated browsers with a persistent identity for AI agents, on your own Windows machine.

- Trust score: 77/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- mcpb · `scalebrowser-0.2.0.mcpb`: 54/100, [markdown](https://verifymcp.io/servers/net-scalebrowser-mcp/https-github-com-blackdiamond-labs-scalebrowser-mcp-releases-download-v0-1-0-sca.md), [page](https://verifymcp.io/servers/net-scalebrowser-mcp/https-github-com-blackdiamond-labs-scalebrowser-mcp-releases-download-v0-1-0-sca)
- npm · `@scalebrowser/mcp`: 77/100 (this document), [markdown](https://verifymcp.io/servers/net-scalebrowser-mcp/scalebrowser-mcp.md), [page](https://verifymcp.io/servers/net-scalebrowser-mcp/scalebrowser-mcp)

## Channel facts

- Registry: `npm`
- Package: `@scalebrowser/mcp`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 19 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1434 tokens (~22/item across 65 items; 65 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 67/100
  - Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "cookie_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 66 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Scalebrowser MCP server?

Scalebrowser runs locally as an npm package, launched with npx -y @scalebrowser/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add net-scalebrowser-mcp -- npx -y @scalebrowser/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "net-scalebrowser-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@scalebrowser/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "net-scalebrowser-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@scalebrowser/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add net-scalebrowser-mcp -- npx -y @scalebrowser/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "net-scalebrowser-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@scalebrowser/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add net-scalebrowser-mcp --command npx --arg -y --arg @scalebrowser/mcp
```

### Hermes

```yaml
mcp_servers:
  net-scalebrowser-mcp:
    command: "npx"
    args: ["-y", "@scalebrowser/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "net-scalebrowser-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@scalebrowser/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add net-scalebrowser-mcp -t stdio -c npx -a -y @scalebrowser/mcp
```

### Other

```json
{
  "mcpServers": {
    "net-scalebrowser-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@scalebrowser/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 72, +5)

- [functional improvement] Stability: unverified → 0.33

### 2026-10-12 (score 67, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-11 (score 67, 0)

- [functional regression] Security disclosure: fail → unverified

## MCP tools (65)

### `lease_profile` (~26 tokens)

Reserve a free profile, start its browser, bind a tab, and return the handle.

### `lease_fleet` (~21 tokens)

The same for several profiles at once, one handle each.

### `lease_renew` (~20 tokens)

Push the reservation's deadline out without losing the handle.

### `start_run` (~26 tokens)

Say in one sentence what this stretch of work is for, so the operator sees it.

### `release_profile` (~22 tokens)

End the reservation and stop the browser. Records how the work went.

### `open_page` (~25 tokens)

Navigate to a public http or https address, and get the full page map back.

### `snapshot` (~25 tokens)

What is on the page now. A diff, unless you ask for a full map.

### `click` (~25 tokens)

Click an element, optionally a point inside it, for a picture rather than a control.

### `press_and_hold` (~21 tokens)

The whole press-and-hold gesture, in one call.

### `type_text` (~22 tokens)

Click a field and type into it at this profile's own cadence.

### `fill_form` (~14 tokens)

Several fields in one call.

### `press_key` (~15 tokens)

A key, including modifier chords.

### `scroll` (~18 tokens)

A real wheel gesture with momentum, not a jump.

### `wait_for` (~28 tokens)

Wait for text or an element to appear, to go, or for the page to go quiet.

### `screenshot` (~23 tokens)

Capture the page or one element, for when the text map cannot describe it.

### `record` (~17 tokens)

Start or stop recording what the browser is doing.

### `video` (~22 tokens)

Turn a recording into a film, and check on one that is rendering.

### `read_value` (~27 tokens)

Read one thing from an element: text, an allowed attribute, a count, a table.

### `read_text` (~25 tokens)

Read the page's prose verbatim, for an article or a thread of comments.

### `interruption_respond` (~25 tokens)

Answer what the browser itself is asking: a permission prompt, a device chooser.

### `secret_list` (~22 tokens)

Which values this profile holds that the agent may use but not read.

### `interact` (~22 tokens)

Hover, drag, upload a file, or choose from a native dropdown.

### `navigate` (~19 tokens)

History and tabs, including the popup a click just opened.

### `measure_frames` (~23 tokens)

How a moving element behaves over time, for a slider or an animation.

### `measure_gap` (~22 tokens)

The distance between two elements, for a puzzle piece and its slot.

### `transcribe_audio` (~23 tokens)

Turn an audio challenge into text, through the operator's own command.

### `measure_rotation` (~20 tokens)

How far an image is turned, for a rotation challenge.

### `interruption_list` (~18 tokens)

What the browser is currently asking, if anything.

### `passkey_list` (~21 tokens)

Which sites this profile can sign in to without a password.

### `passkey_retire` (~22 tokens)

Stop this profile from offering one passkey, for good.

### `cookie_list` (~19 tokens)

The shape of the cookie jar. Never a value.

### `cookie_delete` (~19 tokens)

Remove one cookie, or every cookie of one site.

### `page_report` (~22 tokens)

Console messages and a request summary. Never headers, cookies or bodies.

### `clipboard` (~17 tokens)

Read or write the clipboard of the bound tab.

### `save_pdf` (~17 tokens)

Save the current page as a PDF artifact.

### `download_file` (~19 tokens)

Follow a download and keep the result as an artifact.

### `artifact_list` (~22 tokens)

What this profile has produced: screenshots, downloads, PDFs, recordings.

### `run_list` (~24 tokens)

This profile's earlier runs, so an agent can see what was already tried.

### `profile.list` (~18 tokens)

The profiles on this daemon, with their state.

### `profile.create` (~16 tokens)

Create a profile with a fresh identity.

### `profile.start` (~23 tokens)

Start a profile's browser. Does not give you one you can drive.

### `profile.stop` (~14 tokens)

Stop a profile's browser.

### `profile.update` (~23 tokens)

Change a profile's settings: name, proxy, group, geo mode.

### `input.humanize` (~24 tokens)

Dispatch one humanized gesture at a coordinate, outside the page map.

### `session.export` (~19 tokens)

A profile's session as a password-encrypted bundle.

### `session.import` (~17 tokens)

Unseal such a bundle into a profile.

### `credential.list` (~22 tokens)

Which platforms a profile can log into. Account names, never secrets.

### `group.list` (~15 tokens)

The groups profiles are labelled with.

### `profile.batch` (~25 tokens)

Start, stop, delete, or reassign a proxy or extensions across many profiles.

### `preset.instantiate` (~25 tokens)

Make a fleet from a template: N profiles, each with its own identity.

### `task.list` (~15 tokens)

What is outstanding on a profile.

### `task.add` (~22 tokens)

Put work on a profile's list, for now or for later.

### `task.start` (~16 tokens)

Mark a task as being worked on.

### `task.done` (~18 tokens)

Close a task, with what came of it.

### `task.cancel` (~16 tokens)

Drop a task that no longer applies.

### `proxy.list` (~15 tokens)

The proxy pool. Never credentials.

### `extension.list` (~18 tokens)

The extension library, and what each profile loads.

### `preset.list` (~12 tokens)

The stored templates.

### `group.create` (~12 tokens)

Create a group.

### `group.delete` (~16 tokens)

Delete a group. Its profiles stay.

### `credential_fill` (~23 tokens)

Sign in with this profile's stored login. The agent never receives it.

### `credential_new` (~24 tokens)

Sign up: the daemon draws the password, stores it, and types it.

### `credential_store` (~19 tokens)

Put a login the profile already has into the vault.

### `read_inbox` (~21 tokens)

The profile's confirmation codes, by mail or by text.

### `inbox_open_link` (~27 tokens)

Open a link out of a message, by its number. The address is never shown.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/net-scalebrowser-mcp/scalebrowser-mcp#diagnostics

## Score history

- 2026-10-24: 77
- 2026-10-23: 76
- 2026-10-22: 76
- 2026-10-21: 75
- 2026-10-20: 75
- 2026-10-19: 74
- 2026-10-18: 74
- 2026-10-17: 73
- 2026-10-16: 73
- 2026-10-15: 72
- 2026-10-14: 72
- 2026-10-13: 67
- 2026-10-12: 67
- 2026-10-11: 67
- 2026-10-04: 67

## Common questions

### What is the Scalebrowser MCP server?

Scalebrowser is an MCP server listed in the public MCP registry as net.scalebrowser/mcp. Isolated browsers with a persistent identity for AI agents, on your own Windows machine. This page covers its npm package (@scalebrowser/mcp).

### Is the Scalebrowser MCP server safe to use?

Scalebrowser scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Scalebrowser MCP server expose?

Scalebrowser exposes 65 tools: lease_profile, lease_fleet, lease_renew, start_run, release_profile, and 60 more. Their descriptions and schemas cost roughly 1,333 tokens of context every time the server is loaded.

### Is the Scalebrowser MCP server still maintained?

Scalebrowser is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Scalebrowser MCP server under?

Scalebrowser declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@scalebrowser/mcp
- Socket report: https://socket.dev/npm/package/@scalebrowser/mcp
- Repository: https://github.com/blackdiamond-labs/scalebrowser-mcp
- Website: https://scalebrowser.net/
- Changelog RSS feed: https://verifymcp.io/servers/net-scalebrowser-mcp/scalebrowser-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-scalebrowser-mcp/scalebrowser-mcp.json
- HTML version of this page: https://verifymcp.io/servers/net-scalebrowser-mcp/scalebrowser-mcp