# io.github.Savvy-Tech-Sphere/usable-browser-agent (npm · usable-browser-agent)

MCP server and Firefox add-on that let an AI agent drive your real, logged-in browser. Free tier.

- Trust score: 75/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `usable-browser-agent`: 75/100 (this document), [markdown](https://verifymcp.io/servers/savvy-tech-sphere-usable-browser-agent/usable-browser-agent.md), [page](https://verifymcp.io/servers/savvy-tech-sphere-usable-browser-agent/usable-browser-agent)

## Channel facts

- Registry: `npm`
- Package: `usable-browser-agent`
- Version: `0.7.1`
- 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**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.
  - Actively maintained (last published 43 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 3771 tokens (~71/item across 53 items; 53 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 64% of tool parameters carry a description.
- **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; "browser_workflow_forget" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 53 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 io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server?

io.github.Savvy-Tech-Sphere/usable-browser-agent runs locally as an npm package, launched with npx -y usable-browser-agent. 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 savvy-tech-sphere-usable-browser-agent -- npx -y usable-browser-agent
```

### Cursor

```json
{
  "mcpServers": {
    "savvy-tech-sphere-usable-browser-agent": {
      "command": "npx",
      "args": [
        "-y",
        "usable-browser-agent"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "savvy-tech-sphere-usable-browser-agent": {
      "command": "npx",
      "args": [
        "-y",
        "usable-browser-agent"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add savvy-tech-sphere-usable-browser-agent -- npx -y usable-browser-agent
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "savvy-tech-sphere-usable-browser-agent": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "usable-browser-agent"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add savvy-tech-sphere-usable-browser-agent --command npx --arg -y --arg usable-browser-agent
```

### Hermes

```yaml
mcp_servers:
  savvy-tech-sphere-usable-browser-agent:
    command: "npx"
    args: ["-y", "usable-browser-agent"]
```

### Netclaw

```json
{
  "McpServers": {
    "savvy-tech-sphere-usable-browser-agent": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "usable-browser-agent"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add savvy-tech-sphere-usable-browser-agent -t stdio -c npx -a -y usable-browser-agent
```

### Other

```json
{
  "mcpServers": {
    "savvy-tech-sphere-usable-browser-agent": {
      "command": "npx",
      "args": [
        "-y",
        "usable-browser-agent"
      ]
    }
  }
}
```

## 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.

### 2026-11-02 (score 75, +1)

- [security] Stability: 0.97 → pass

### 2026-11-01 (score 74, −1)

- [functional] Stability: pass → 0.97

### 2026-10-26 (score 75, +1)

- [security] Stability: 0.97 → pass

### 2026-10-24 (score 74, −5)

- [security regression] CVE-2023-54404 affects this package: high
- [security regression] Known CVEs: pass → fail

### 2026-10-23 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (53)

### `browser_workflow_recall` (~133 tokens)

Search local workflow memory BEFORE starting any multi-step or repeated browser task. Use this first for changing sites like app stores, admin consoles, checkout flows, dashboards, or any task you may have done before.

Input parameters:

- `limit` (number): Maximum matches to return (1-10, default 5).
- `query` (string): Task objective or memory id, e.g. 'create a new app in Google Play Console'.
- `site` (string): Site name or domain, e.g. 'Google Play Console' or 'play.google.com'.
- `tags` (array): Optional tags to narrow recall.

### `browser_workflow_remember` (~298 tokens)

Save the verified reusable workflow after discovering or completing a browser task. Store durable UI labels, decisions, and pitfalls; do not store passwords, one-time codes, or transient [ref=eN] handles.

Input parameters:

- `confidence` (string): Confidence that the workflow is reusable.
- `domain` (string): Domain, e.g. 'play.google.com'.
- `lastVerified` (string): Verification date, default today.
- `notes` (string): Short extra context for future agents.
- `outcome` (string): What succeeded or what state was reached.
- `pitfalls` (array): Things that were wrong, surprising, changed, or easy to miss.
- `selectors` (array): Durable UI cues: visible labels, section names, field names. Avoid transient refs.
- `site` (string): Human site name, e.g. 'Google Play Console'.
- `steps` (array, required): Ordered durable steps that worked. Use visible labels and page names, not transient refs.
- `supersedes` (array): Workflow memory ids this record replaces because they are stale or incomplete.
- `tags` (array): Search tags such as 'android', 'play-store', 'release'.
- `task` (string, required): Reusable task objective, e.g. 'Create a new Android app in Google Play Console'.
- `title` (string): Page title where the workflow starts or was verified.
- `url` (string): Useful starting URL if stable.

### `browser_workflow_forget` (~78 tokens)

Remove a stale, sensitive, or incorrect workflow memory by id. This appends a local tombstone; normal recall will stop returning that memory.

Input parameters:

- `id` (string, required): Workflow memory id, e.g. wm_20260604123000_ab12cd34.
- `reason` (string): Optional short reason for the deletion.

### `browser_native_status` (~50 tokens)

Report which OS-level input capabilities are available (trusted keystrokes, native-dialog control, raw clicks) and any setup needed. Check this before relying on the browser_os_* / browser_native_dialog tools.

### `browser_os_type` (~83 tokens)

Type text using REAL OS keystrokes into whatever currently has focus. Use only when in-page typing fails because the element checks event.isTrusted (some payment fields, editors, games). Focus the field first (e.g. browser_click), then call this. macOS only; needs Accessibility permission.

Input parameters:

- `modifiers` (array)
- `text` (string, required)

### `browser_os_key` (~66 tokens)

Press a REAL OS key (Enter, Tab, Escape, ArrowDown, F1-F8, or a single char), optionally with modifiers. For native UI and isTrusted-checking pages. macOS only.

Input parameters:

- `key` (string, required)
- `modifiers` (array)

### `browser_os_click` (~81 tokens)

Click at absolute screen coordinates with a REAL OS mouse event. Prefer browser_click; use this only for trusted clicks or native chrome. macOS only; raw clicks need `brew install cliclick`.

Input parameters:

- `button` (string)
- `count` (number): 2 = double-click.
- `x` (number, required)
- `y` (number, required)

### `browser_os_click_ref` (~174 tokens)

Click a page element by ref with a REAL, OS-trusted mouse event (for elements that ignore synthetic clicks). Computes the element's on-screen position via the connected browser, raises its window, then clicks. On Firefox coordinates are exact; on Chrome they are approximate (refused unless allowApproximate is set) and iframe elements are not supported. macOS only; needs cliclick + Accessibility permission.

Input parameters:

- `allowApproximate` (boolean): Chrome only: opt in to clicking at APPROXIMATE screen coordinates (no exact viewport-origin API exists there). Only set this after visually confirming the window is a normal browser window (no docked…
- `button` (string)
- `count` (number)
- `ref` (string, required)

### `browser_native_dialog` (~133 tokens)

Inspect or operate a NATIVE browser dialog that no extension can touch — the file picker, print dialog, basic-auth popup, or 'Leave page?'. action='list' shows the dialog's buttons; 'click_button' presses one by name (e.g. 'Open', 'Save', 'Don't Save'); 'set_text' types into the focused dialog field. macOS only; needs Accessibility permission.

Input parameters:

- `action` (string)
- `button` (string): Button label for click_button.
- `process` (string): Process name (default firefox).
- `text` (string): Text for set_text.

### `browser_focus_browser` (~38 tokens)

Bring the connected browser (Firefox or Chrome, per the bridge connection) to the foreground so OS-level input lands in it. macOS only.

### `browser_request_human_help` (~142 tokens)

Hand control to the human for something automation must not or cannot do — CAPTCHAs, anti-bot 'verify you're human' walls, 2FA approvals, or a deliberate judgment call. Sends a desktop notification and returns a message you should relay to the user, then STOP and wait for them to act before continuing. Do not attempt to bypass CAPTCHAs yourself.

Input parameters:

- `message` (string, required): What you need the human to do, e.g. 'Solve the CAPTCHA on the login page, then tell me to continue.'
- `reason` (string): Short category, e.g. 'captcha', '2fa', 'permission'.

### `browser_snapshot` (~96 tokens)

Capture an accessibility/DOM snapshot of the active Firefox tab as a structured tree. Each interactive element gets a stable [ref=eN] handle. USE THIS to understand the page before acting, and re-run it after the page changes — refs become stale after navigation or DOM updates. If workflow-memory hints appear, call browser_workflow_recall before continuing.

Input parameters:

- `maxNodes` (number): Max nodes to include (default 1500).

### `browser_navigate` (~43 tokens)

Navigate the active tab to a URL and wait for it to finish loading.

Input parameters:

- `timeout` (number)
- `url` (string, required): Full URL including https://

### `browser_back` (~17 tokens)

Go back in the active tab's history.

### `browser_forward` (~17 tokens)

Go forward in the active tab's history.

### `browser_reload` (~13 tokens)

Reload the active tab.

### `browser_click` (~118 tokens)

Click an element by its ref from the latest snapshot. Supports right/middle button, double-click, and modifier keys (ctrl/shift/alt/meta) for context menus, multi-select, and open-in-new-tab.

Input parameters:

- `button` (string): Mouse button (default left). 'right' opens context menus.
- `count` (number): Click count; 2 = double-click.
- `modifiers` (array): Modifier keys held during the click.
- `ref` (string, required): Element ref, e.g. e12, from browser_snapshot.

### `browser_drag` (~75 tokens)

Drag one element onto another (kanban cards, sortable lists, file tiles, sliders). Fires both HTML5 drag-and-drop and a pointer-drag sequence so native and JS-library targets both respond.

Input parameters:

- `fromRef` (string, required): Ref of the element to drag.
- `toRef` (string, required): Ref of the drop target.

### `browser_type` (~75 tokens)

Focus a text field by ref and type text into it. Set submit=true to press Enter afterward (e.g. to submit a search).

Input parameters:

- `clear` (boolean): Clear the field first (default true).
- `ref` (string, required)
- `submit` (boolean): Press Enter after typing.
- `text` (string, required)

### `browser_fill_form` (~46 tokens)

Fill multiple fields in one call. Pass fields as an array of {ref, text}. Faster and more reliable than many browser_type calls for forms.

Input parameters:

- `fields` (array, required)

### `browser_fill_secret` (~88 tokens)

Fill a username or password field from the server-side credential broker. Pass only a secret alias; secret values are never accepted as tool input or returned.

Input parameters:

- `field` (string): Which secret field to fill (default password).
- `ref` (string, required): Element ref, e.g. e12, from browser_snapshot.
- `secret` (string, required): Secret alias from the server-side secrets vault.

### `browser_login` (~126 tokens)

Atomically fill username/password fields from a server-side secret alias and submit the login form. Pass only refs and the secret alias; secret values are never accepted as tool input or returned.

Input parameters:

- `password_ref` (string, required): Password field ref, e.g. e12, from browser_snapshot.
- `secret` (string, required): Secret alias from the server-side secrets vault.
- `submit_ref` (string): Submit button ref. If omitted, the password field's enclosing form is submitted.
- `username_ref` (string): Username field ref. Filled only when provided and the secret has a username.

### `browser_select` (~37 tokens)

Choose an option in a <select> dropdown by visible label or value.

Input parameters:

- `ref` (string, required)
- `value` (string, required)

### `browser_hover` (~24 tokens)

Hover the pointer over an element by ref.

Input parameters:

- `ref` (string, required)

### `browser_press_key` (~53 tokens)

Press a key (Enter, Tab, Escape, ArrowDown, etc.). Optionally target an element by ref; otherwise the focused element receives it.

Input parameters:

- `key` (string, required)
- `ref` (string)

### `browser_clipboard_read` (~45 tokens)

Read text from the system clipboard. Use after the page put something on the clipboard (e.g. a 'Copy' button) or to move data between pages and apps.

### `browser_clipboard_write` (~24 tokens)

Write text to the system clipboard.

Input parameters:

- `text` (string, required)

### `browser_paste` (~81 tokens)

Paste into an element by ref as a real paste event — rich editors (Google Docs, Notion, contenteditable) handle this better than typing. Pastes the given text, or the current clipboard contents when text is omitted.

Input parameters:

- `ref` (string, required)
- `text` (string): Text to paste. Omit to paste the current clipboard contents.

### `browser_clipboard_read_image` (~47 tokens)

Read an image from the system clipboard (e.g. after a 'Copy image' action) and return it as a PNG/JPEG. Errors if the clipboard holds no image.

### `browser_clipboard_write_image` (~43 tokens)

Put a local image file onto the system clipboard so it can be pasted into a page.

Input parameters:

- `path` (string, required): Absolute path to a local image file.

### `browser_set_dialog_policy` (~118 tokens)

Set how native JS dialogs are auto-answered so they never block the agent. accept=true confirms (default), promptText sets what prompt() returns, suppress=true neutralizes 'Leave page?' beforeunload guards. Applies to the current page; re-set after navigation if needed.

Input parameters:

- `accept` (boolean): Answer confirm()/prompt() affirmatively (default true).
- `promptText` (string): Value returned from prompt() when accepted.
- `suppress` (boolean): Neutralize beforeunload 'leave page?' guards (default true).

### `browser_dialogs` (~43 tokens)

List native JS dialogs (alert/confirm/prompt) the page tried to open and how they were auto-answered. Use this to see if the page asked something.

### `browser_mock_geolocation` (~91 tokens)

Make navigator.geolocation return a fixed position (so location-gated tasks proceed without the native permission prompt). Pass clear=true to stop mocking. Applies to the current page; re-set after navigation.

Input parameters:

- `accuracy` (number): Accuracy in meters (default 20).
- `clear` (boolean): Stop mocking and restore real geolocation.
- `latitude` (number)
- `longitude` (number)

### `browser_download` (~95 tokens)

Download a file to disk WITHOUT the OS save dialog, and return its local path so you can read it. Use for PDFs, exports, attachments — the file lands in the browser's downloads folder.

Input parameters:

- `filename` (string): Optional filename (relative to the downloads folder).
- `timeout` (number): Max ms to wait for completion (default 60000).
- `url` (string, required): Full URL of the file to download.

### `browser_downloads_list` (~29 tokens)

List recent downloads with their on-disk paths and state.

Input parameters:

- `limit` (number)

### `browser_save_pdf` (~59 tokens)

Save the current tab as a PDF to the downloads folder (dialog-free). Useful to capture a rendered page. If your Firefox build still shows a save dialog, use browser_native_dialog to confirm it.

Input parameters:

- `filename` (string): Optional output filename.

### `browser_network_log` (~120 tokens)

Inspect recent network requests (method, URL, status, type, errors) the browser made. Use to diagnose why a button 'did nothing', find an API endpoint, or confirm a request succeeded.

Input parameters:

- `filter` (string): Only requests whose URL contains this substring.
- `limit` (number): Max requests to return (default 50).
- `onlyErrors` (boolean): Only failed requests (network error or status >= 400).
- `type` (string): Resource type, e.g. xmlhttprequest, script, document, image.

### `browser_http_auth` (~93 tokens)

Arm answers for HTTP basic-auth prompts (the native username/password dialog) from a server-side secret alias, scoped to that secret's domains. Pass only the alias; the credential value is never accepted as input or returned. Call before navigating to the protected URL.

Input parameters:

- `once` (boolean): Answer only the next auth challenge, then disarm.
- `secret` (string, required): Secret alias from the server-side secrets vault.

### `browser_clear_http_auth` (~34 tokens)

Disarm previously-armed HTTP basic-auth answers (all domains, or specific ones).

Input parameters:

- `domains` (array)

### `browser_upload_file` (~163 tokens)

Attach local file(s) to the page WITHOUT opening the OS file picker (the picker cannot be automated — never click elements that open it). Pass the ref of a file input (hidden ones appear in snapshots as 'file-input ... [hidden]'), or of an upload button/dropzone near it, plus absolute local file paths. Sets the input's files directly, or simulates a drag-and-drop when no file input is found.

Input parameters:

- `mode` (string): auto (default): find and fill the file input. drop: force a drag-and-drop onto the ref'd element (for dropzones).
- `paths` (array, required): Absolute paths of local files to attach.
- `ref` (string, required): Ref of the file input, upload button, or dropzone.

### `browser_scroll` (~112 tokens)

Scroll the page or a specific scrollable container. Pass a ref to scroll that container (inner panes, virtualized/infinite lists); omit it to scroll the window. Use to='bottom' to jump to the end (e.g. trigger infinite-scroll loading).

Input parameters:

- `amount` (number)
- `direction` (string)
- `ref` (string): Scroll this container (or, with no direction/to, just reveal it).
- `to` (string): Jump to the top or bottom of the target.

### `browser_read_text` (~52 tokens)

Get the visible text of the page (or of one element by ref). Use for reading article/content; use browser_snapshot for interactive structure.

Input parameters:

- `maxChars` (number)
- `ref` (string)

### `browser_get_value` (~29 tokens)

Get the current value/text of a field or element by ref.

Input parameters:

- `ref` (string, required)

### `browser_wait` (~26 tokens)

Wait a fixed number of milliseconds (use sparingly).

Input parameters:

- `ms` (number, required)

### `browser_wait_for_text` (~38 tokens)

Wait until the given text appears anywhere on the page (or timeout).

Input parameters:

- `text` (string, required)
- `timeout` (number)

### `browser_list_tabs` (~22 tokens)

List all open tabs with their ids, urls, and titles.

### `browser_select_tab` (~32 tokens)

Make a tab active by id (the agent acts on the active tab).

Input parameters:

- `tabId` (number, required)

### `browser_new_tab` (~31 tokens)

Open a new tab, optionally at a URL, and make it active.

Input parameters:

- `url` (string)

### `browser_close_tab` (~29 tokens)

Close a tab by id (defaults to the active tab).

Input parameters:

- `tabId` (number)

### `browser_status` (~31 tokens)

Check the bridge connection and the current active tab. If the active tab has workflow memories, this returns short hints.

### `browser_info` (~31 tokens)

Get the active tab's url, title, load state, scroll position, and short workflow-memory hints when available.

### `browser_screenshot` (~40 tokens)

Capture a PNG screenshot of the visible part of the active tab. Use only when the snapshot is insufficient (e.g. canvas, charts, visual layout).

### `browser_eval` (~109 tokens)

Run JavaScript in the page and return the result. Disabled under hardened mode, which is the default; the operator enables it by setting UBA_STRICT_SECRETS=0 in the server environment. On Firefox the code runs in the content-script sandbox; on Chrome it runs in the page's own realm, where the page can observe it and its CSP applies. Use only when no dedicated tool fits.

Input parameters:

- `code` (string, required): JS body; use `return value;` to return data.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/savvy-tech-sphere-usable-browser-agent/usable-browser-agent#diagnostics

## Score history

- 2026-11-05: 75
- 2026-11-04: 75
- 2026-11-03: 75
- 2026-11-02: 75
- 2026-11-01: 74
- 2026-10-31: 75
- 2026-10-30: 75
- 2026-10-29: 75
- 2026-10-28: 75
- 2026-10-27: 75
- 2026-10-26: 75
- 2026-10-25: 74
- 2026-10-24: 74
- 2026-10-23: 79
- 2026-10-22: 78
- 2026-10-21: 78
- 2026-10-20: 77
- 2026-10-19: 77
- 2026-10-18: 76
- 2026-10-17: 76
- 2026-10-16: 75
- 2026-10-15: 75
- 2026-10-14: 74
- 2026-10-13: 74
- 2026-10-12: 73
- 2026-10-06: 71
- 2026-10-04: 70
- 2026-10-03: 66
- 2026-10-02: 66
- 2026-10-01: 66

## Common questions

### What is the io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server?

io.github.Savvy-Tech-Sphere/usable-browser-agent is an MCP server listed in the public MCP registry as io.github.Savvy-Tech-Sphere/usable-browser-agent. MCP server and Firefox add-on that let an AI agent drive your real, logged-in browser. Free tier. This page covers its npm package (usable-browser-agent).

### Is the io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server safe to use?

io.github.Savvy-Tech-Sphere/usable-browser-agent scores 75 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 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 io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server expose?

io.github.Savvy-Tech-Sphere/usable-browser-agent exposes 53 tools: browser_workflow_recall, browser_workflow_remember, browser_workflow_forget, browser_native_status, browser_os_type, and 48 more. Their descriptions and schemas cost roughly 3,771 tokens of context every time the server is loaded.

### Is the io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server still maintained?

io.github.Savvy-Tech-Sphere/usable-browser-agent 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.

## Links

- npm package: https://www.npmjs.com/package/usable-browser-agent
- Socket report: https://socket.dev/npm/package/usable-browser-agent
- Repository: https://github.com/Savvy-Tech-Sphere/usable-browser-agent-free
- Website: https://savvytechsphere.com/usable-browser-agent
- Changelog RSS feed: https://verifymcp.io/servers/savvy-tech-sphere-usable-browser-agent/usable-browser-agent.xml
- Changelog JSON feed: https://verifymcp.io/servers/savvy-tech-sphere-usable-browser-agent/usable-browser-agent.json
- HTML version of this page: https://verifymcp.io/servers/savvy-tech-sphere-usable-browser-agent/usable-browser-agent