# MCP Browser Extension (npm · mcp-browser-extension)

Drive your real Chrome over MCP: real logins and cookies, multi-tab automation, deny-all by default.

- Trust score: 88/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `mcp-browser-extension`: 88/100 (this document), [markdown](https://verifymcp.io/servers/mehmoodqureshi-mcp-browser-extension/mcp-browser-extension.md), [page](https://verifymcp.io/servers/mehmoodqureshi-mcp-browser-extension/mcp-browser-extension)

## Channel facts

- Registry: `npm`
- Package: `mcp-browser-extension`
- Version: `0.9.38`
- 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 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 41 of 129 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Mehmoodqureshi/mcp-browser-extension).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2754 tokens (~125/item across 22 items; 22 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 68% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 23 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 MCP Browser Extension server?

MCP Browser Extension runs locally as an npm package, launched with npx -y mcp-browser-extension. 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 mehmoodqureshi-mcp-browser-extension -- npx -y mcp-browser-extension
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "mehmoodqureshi-mcp-browser-extension": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-browser-extension"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mehmoodqureshi-mcp-browser-extension -- npx -y mcp-browser-extension
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add mehmoodqureshi-mcp-browser-extension --command npx --arg -y --arg mcp-browser-extension
```

### Hermes

```yaml
mcp_servers:
  mehmoodqureshi-mcp-browser-extension:
    command: "npx"
    args: ["-y", "mcp-browser-extension"]
```

### Netclaw

```json
{
  "McpServers": {
    "mehmoodqureshi-mcp-browser-extension": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mcp-browser-extension"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mehmoodqureshi-mcp-browser-extension -t stdio -c npx -a -y mcp-browser-extension
```

### Other

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

## 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.

### 2026-11-05 (score 88, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.85

### 2026-11-04 (score 77, −10)

- [security regression] Known CVEs: pass → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.63 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Dependency health: 0.87 → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.9.36 → 0.9.38

### 2026-11-03 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 85, +26)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.87

### 2026-10-28 (score 59, −25)

- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [functional regression] Dependency health: 0.87 → unverified
- [functional] Package version: 0.9.34 → 0.9.36

### 2026-10-27 (score 84, +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.

### 2026-10-25 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (22)

### `tabs_list` (~13 tokens)

List open browser tabs.

### `screenshot` (~182 tokens)

Capture a screenshot (page or element). Default is JPEG (quality 70) at CSS-pixel size, which is several times smaller than PNG and reads fine. Pass format:"png" for lossless, quality 1-100 for JPEG, scale 2 for device pixels on a Retina display or 0.5 to shrink.

Input parameters:

- `allFrames` (boolean): Act on the first match in ANY frame (the element may be in an iframe)
- `format` (string)
- `frameId` (number): Frame id from frames_list
- `fullPage` (boolean)
- `quality` (number)
- `ref` (string): Element ref from a snapshot
- `scale` (number)
- `selector` (string): CSS selector (or pass ref)
- `tabId` (string): Tab id (default: agent's tab)

### `get_text` (~126 tokens)

Get visible text of the page or an element.

Input parameters:

- `allFrames` (boolean): Act on the first match in ANY frame (the element may be in an iframe)
- `frameId` (number): Frame id from frames_list
- `maxBytes` (number): Cap returned content at N UTF-8 bytes (default 262144); the full payload still lands in results/
- `ref` (string): Element ref from a snapshot
- `selector` (string): CSS selector (or pass ref)
- `tabId` (string): Tab id (default: agent's tab)

### `get_html` (~170 tokens)

Get HTML of the page or an element. Output is capped (see maxBytes) and cut at a tag boundary; narrow it with `selector` rather than raising the cap when you can. Password field values are always blanked.

Input parameters:

- `allFrames` (boolean): Act on the first match in ANY frame (the element may be in an iframe)
- `frameId` (number): Frame id from frames_list
- `maxBytes` (number): Cap returned content at N UTF-8 bytes (default 262144); the full payload still lands in results/
- `outer` (boolean)
- `ref` (string): Element ref from a snapshot
- `selector` (string): CSS selector (or pass ref)
- `tabId` (string): Tab id (default: agent's tab)

### `snapshot` (~183 tokens)

Accessibility snapshot: interactive elements with refs to target by `ref` (more reliable than guessing CSS selectors). Pass diff:true to get only what changed since the last snapshot of this tab - far cheaper in a click/read loop. Password fields appear as secret:true with no value.

Input parameters:

- `allFrames` (boolean): Act on the first match in ANY frame (the element may be in an iframe)
- `diff` (boolean): Return added/removed/changed elements since the previous snapshot of this tab instead of the whole tree
- `failOnAuthWall` (boolean): Error with [AUTH_REQUIRED] if this lands on a sign-in wall (expired session)
- `frameId` (number): Frame id from frames_list
- `interactiveOnly` (boolean)
- `max` (number)
- `tabId` (string): Tab id (default: agent's tab)

### `page_watch` (~87 tokens)

Save a local page checkpoint and compare it later. Actions: create (name), compare (watchId), list, delete. Stores accessibility labels and state, never form values. Site allowlist still applies.

Input parameters:

- `action` (string, required)
- `name` (string)
- `tabId` (string): Tab id (default: agent's tab)
- `watchId` (string)

### `get_cookies` (~49 tokens)

Cookies for the tab's URL (or url); values need --enable-cookie-values.

Input parameters:

- `tabId` (string): Tab id (default: agent's tab)
- `url` (string)

### `storage` (~70 tokens)

Read/write localStorage (or sessionStorage). op: get|set|remove|clear.

Input parameters:

- `key` (string)
- `op` (string, required)
- `session` (boolean)
- `tabId` (string): Tab id (default: agent's tab)
- `value` (string)

### `wait_for` (~129 tokens)

Wait for a selector or text to appear/disappear.

Input parameters:

- `allFrames` (boolean): Act on the first match in ANY frame (the element may be in an iframe)
- `failOnAuthWall` (boolean): Error with [AUTH_REQUIRED] if this lands on a sign-in wall (expired session)
- `frameId` (number): Frame id from frames_list
- `gone` (boolean)
- `selector` (string)
- `tabId` (string): Tab id (default: agent's tab)
- `textContains` (string)
- `timeoutMs` (number)

### `extract_links` (~120 tokens)

Extract anchors from the page or a subtree. dedupe=true collapses links sharing an href (nav/footer noise); limit caps the count.

Input parameters:

- `allFrames` (boolean): Act on the first match in ANY frame (the element may be in an iframe)
- `dedupe` (boolean)
- `frameId` (number): Frame id from frames_list
- `limit` (number)
- `sameOriginOnly` (boolean)
- `selector` (string)
- `tabId` (string): Tab id (default: agent's tab)

### `read_as_markdown` (~111 tokens)

Read the page (or subtree) as readable markdown.

Input parameters:

- `allFrames` (boolean): Act on the first match in ANY frame (the element may be in an iframe)
- `frameId` (number): Frame id from frames_list
- `maxBytes` (number): Cap returned content at N UTF-8 bytes (default 262144); the full payload still lands in results/
- `selector` (string)
- `tabId` (string): Tab id (default: agent's tab)

### `frames_list` (~88 tokens)

List the tab's frames (the top document plus every iframe the extension can reach), with each frame's id and URL. Use it when a selector that should match does not: the element is probably in one of these frames, and you can then pass frameId (or allFrames:true) to act inside it.

Input parameters:

- `tabId` (string): Tab id (default: agent's tab)

### `print_pdf` (~149 tokens)

Render the page to PDF through Chrome's own print pipeline and save it to the task's results/ dir. Returns the path and size, not the bytes - a PDF is not something to spend context on.

Input parameters:

- `landscape` (boolean)
- `pageRanges` (string): e.g. '1-3, 5'
- `paperHeight` (number): Inches
- `paperWidth` (number): Inches
- `preferCSSPageSize` (boolean)
- `printBackground` (boolean): Include background graphics (default true)
- `scale` (number): 0.1 - 2.0
- `tabId` (string): Tab id (default: agent's tab)

### `proxy_status` (~36 tokens)

The active profile's proxy and the IP sites see. The user sets it per Chrome profile; for another IP, profile_use another profile.

### `chrome_status` (~29 tokens)

Report backend/session status: paired browser profiles and how each was named, and flags for switched-off capabilities.

### `auth_check` (~182 tokens)

Is the tab sitting on a sign-in wall? Reads the page (URL, title, password fields, sign-in controls) and returns { authRequired, confidence, signals }. Use it after a navigate, or whenever a step fails unexpectedly, to tell "the session expired" apart from "the agent got lost". Pass failOnAuthWall:true to get an [AUTH_REQUIRED] error instead of a verdict, so a harness can bucket the run as an auth failure.

Input parameters:

- `allFrames` (boolean): Act on the first match in ANY frame (the element may be in an iframe)
- `failOnAuthWall` (boolean): Error with [AUTH_REQUIRED] if this lands on a sign-in wall (expired session)
- `frameId` (number): Frame id from frames_list
- `tabId` (string): Tab id (default: agent's tab)

### `profile_use` (~73 tokens)

Switch the active browser profile (identity). Subsequent downloads, results, screenshots, and the action log are stored under profiles/<name>/. Resets the active task to "default" unless you then call task_new.

Input parameters:

- `name` (string, required): Profile name (becomes a folder; sanitized to a safe path segment).

### `profile_rename` (~62 tokens)

Rename an automatically named browser profile (e.g. "profile-2" -> "work"). The name sticks across restarts; its saved artifacts move with it.

Input parameters:

- `from` (string, required): Current profile name
- `to` (string, required): New profile name

### `task_new` (~70 tokens)

Start a new task (run) under the active profile. Creates profiles/<profile>/tasks/<name>/ with downloads/, results/, screenshots/ and makes it the active task so all captured artifacts land there.

Input parameters:

- `name` (string, required): Task name (becomes a folder; sanitized to a safe path segment).

### `tasks_list` (~25 tokens)

List every task across all profiles under the data dir, with sizes and download counts.

### `task_status` (~25 tokens)

Report the active profile/task and the folder paths where this run's artifacts are stored.

### `batch` (~223 tokens)

Run multiple tool calls in one request — parallel (default) or serial. Each op is { tool, args } and goes through the same policy gate, rate limit, and error handling as a direct call. In parallel mode, tab-scoped ops MUST pass an explicit tabId (the active-tab default is unsafe under concurrency). Use to drive several tabs at once (e.g. open tabs, then batch get_text across them). Cannot be nested.

Input parameters:

- `maxConcurrency` (number): Parallel mode: max ops in flight at once (default 6).
- `maxResultBytes` (number): Total payload budget across all ops (default 1048576). Ops past the budget are replaced by a one-line summary instead of their content, so a 50-op screenshot/get_html batch cannot flood the caller.
- `mode` (string): Default "parallel".
- `ops` (array, required): Operations to run; each is a tool name + its args.
- `stopOnError` (boolean): Serial mode only: stop after the first failing op (the rest are skipped).

## Diagnostics

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

## Score history

- 2026-11-05: 88
- 2026-11-04: 77
- 2026-11-03: 87
- 2026-11-02: 86
- 2026-11-01: 86
- 2026-10-31: 85
- 2026-10-30: 85
- 2026-10-29: 85
- 2026-10-28: 59
- 2026-10-27: 84
- 2026-10-26: 83
- 2026-10-25: 83
- 2026-10-24: 82
- 2026-10-23: 82
- 2026-10-22: 81
- 2026-10-21: 66
- 2026-10-20: 55
- 2026-10-19: 80
- 2026-10-18: 69
- 2026-10-17: 80
- 2026-10-16: 64
- 2026-10-15: 79

## Common questions

### What is the MCP Browser Extension server?

MCP Browser Extension is listed in the public MCP registry as io.github.Mehmoodqureshi/mcp-browser-extension. Drive your real Chrome over MCP: real logins and cookies, multi-tab automation, deny-all by default. This page covers its npm package (mcp-browser-extension).

### Is the MCP Browser Extension server safe to use?

MCP Browser Extension scores 88 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 MCP Browser Extension server expose?

MCP Browser Extension exposes 22 tools: tabs_list, screenshot, get_text, get_html, snapshot, and 17 more. Their descriptions and schemas cost roughly 2,202 tokens of context every time the server is loaded.

### Is the MCP Browser Extension server still maintained?

MCP Browser Extension is still listed as active in the MCP registry. We last reached this channel on 5 November 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 MCP Browser Extension server under?

MCP Browser Extension 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/mcp-browser-extension
- Socket report: https://socket.dev/npm/package/mcp-browser-extension
- Repository: https://github.com/Mehmoodqureshi/mcp-browser-extension
- Website: https://mcp-browser-extension.com/
- Changelog RSS feed: https://verifymcp.io/servers/mehmoodqureshi-mcp-browser-extension/mcp-browser-extension.xml
- Changelog JSON feed: https://verifymcp.io/servers/mehmoodqureshi-mcp-browser-extension/mcp-browser-extension.json
- HTML version of this page: https://verifymcp.io/servers/mehmoodqureshi-mcp-browser-extension/mcp-browser-extension