Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Public Browser

NPM · PUBLIC-BROWSER · SCANNED SEP 20

Browse your real profile: -30% tokens, -25% cost, -41% tool calls, -34% tool defs, +40% faster

Available components

+4 this week 79 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 32 of 98 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 5 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability77
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 3716 tokens (~148/item across 25 items; 25 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
  • Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 25 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 26 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Public Browser MCP server?

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

npm · public-browser

# add to Claude Code
claude mcp add silbercue-public-browser -- npx -y public-browser
// .cursor/mcp.json
{
  "mcpServers": {
    "silbercue-public-browser": {
      "command": "npx",
      "args": [
        "-y",
        "public-browser"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "silbercue-public-browser": {
      "command": "npx",
      "args": [
        "-y",
        "public-browser"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add silbercue-public-browser -- npx -y public-browser
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "silbercue-public-browser": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "public-browser"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add silbercue-public-browser --command npx --arg -y --arg public-browser
# ~/.hermes/config.yaml
mcp_servers:
  silbercue-public-browser:
    command: "npx"
    args: ["-y", "public-browser"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "silbercue-public-browser": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "public-browser"
      ]
    }
  }
}
# add to Vellum
assistant mcp add silbercue-public-browser -t stdio -c npx -a -y public-browser
// mcp.json
{
  "mcpServers": {
    "silbercue-public-browser": {
      "command": "npx",
      "args": [
        "-y",
        "public-browser"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +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.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −14
    • Malware scan: pass → unverified security
    • Tool safety: pass → unverified security
    • Stability: 0.33 → unverified security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • First check of Schema quality: unverified functional
    • Package version: 2.10.5 → 2.10.6 functional
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/public-browser@2.10.6

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 98 packages
Packages resolved 98
Stale 32
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 25 exposed · ~3,155 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
batch_evaluate ~133

Visit several URLs in sequence and run the same JS expression on each. For controlled checks across known pages where view_page/run_plan would be too chatty; not for normal reading, clicking or form work.

NameTypeReqDescription
continue_on_errorbooleanContinue with the remaining URLs if one fails
evaluate_per_pagestringyesJS expression evaluated on each page
settle_msnumberWait in ms after each page load before evaluating
timeout_per_page_msnumberTimeout per page in ms (navigate+settle+evaluate)
urlsarrayyesURLs to visit in order

No output schema declared.

No examples provided.

capture_image ~101

Pixel-level screenshot (WebP, max 800px, <100KB). Only for canvas or chart content without DOM text, pixel-level rendering or animation checks, or when the user explicitly asks for a screenshot. Returns no refs and reads no text — that is view_page.

NameTypeReqDescription
full_pagebooleanCapture the full scrollable page, not just the viewport
sombooleanOverlay numbered labels matching view_page refs (Set-of-Mark)

No output schema declared.

No examples provided.

click ~183

Click an element by ref, CSS selector, visible text, or viewport x/y (canvas, pixel-precise targets). Dispatches real CDP mouse events. A click that opens a new tab is reported in the response. The DOM diff (NEW/REMOVED/CHANGED) arrives with the next response, or in this one with wait_for_diff: true.

NameTypeReqDescription
refstringElement ref (preferred)
selectorstringCSS selector (fallback)
textstringVisible text (a11y name); no view_page needed, prefers interactive
wait_for_diffbooleanWait for the DOM diff before returning (default false, slower)
xnumberViewport X in px; with y, not ref/selector
ynumberViewport Y in px; use with x

No output schema declared.

No examples provided.

configure_session ~135

View or set session defaults for recurring parameters (tab, timeout, …). Without params: show current defaults and auto-promote suggestions; autoPromote: true applies them. Set profile BEFORE any browser interaction to launch Chrome with a named profile.

NameTypeReqDescription
autoPromotebooleanApply all current auto-promote suggestions
defaultsobjectParam name → default value; null removes a default
profilestringChrome profile name (list them with: public-browser profiles); restart: true switches mid-session
restartbooleanRestart Chrome with the new profile even if running; closes all tabs

No output schema declared.

No examples provided.

console_logs ~70

Read collected browser console logs; filter by level (info/warning/error/debug) and/or regex; optionally clear the buffer after reading.

NameTypeReqDescription
clearbooleanClear the buffer after reading
levelstringFilter by log level
patternstringRegex matched against log text

No output schema declared.

No examples provided.

dom_snapshot ~59

Structured layout data: bounding boxes, computed styles, paint order, colors; refs match view_page. Only for spatial questions view_page cannot answer (is A above B? what color?).

NameTypeReqDescription
refstringElement ref for a subtree snapshot

No output schema declared.

No examples provided.

download ~141

Wait for pending downloads or list this session's downloaded files. Downloads start by themselves when you click a download link or open a file URL (PDF, CSV, …); this tool never triggers them. download() waits for a pending download to finish; download({ action: 'list' }) returns at once.

NameTypeReqDescription
actionstringstatus waits for pending downloads; list: history, never waits (use for polling)
settlenumberMs to wait for a download to START before reporting none — Chrome fires downloadWillBegin a few ms after the click; 0 = instant
timeoutnumberMax wait in ms for pending downloads

No output schema declared.

No examples provided.

drag ~235

Drag via native CDP mouse events. Works for CSS-driven drag: slider thumbs, resize handles, text selection, mouse-based reorder lists (SortableJS in mouse mode). NOT for the HTML5 Drag&Drop API (draggable=true with dragstart/drop listeners, React DnD HTML5Backend, Vuedraggable, ng2-dnd) — that needs Input.dispatchDragEvent. Source: from_ref/from_selector or from_x+from_y; target: to_ref/to_selector or to_x+to_y.

NameTypeReqDescription
from_refstringSource element ref
from_selectorstringSource CSS selector
from_xnumberSource viewport X in px (with from_y)
from_ynumberSource viewport Y in px
stepsintegerNative mouseMoved events between press and release; minimum 5
to_refstringTarget element ref
to_selectorstringTarget CSS selector
to_xnumberTarget viewport X in px (with to_y)
to_ynumberTarget viewport Y in px

No output schema declared.

No examples provided.

evaluate ~112

Run JavaScript in the page. Good uses: computation, style mutations (.style.X = ..., classList), shadow-root traversal, in-page fetch(), app-specific side effects no dedicated tool covers. Scope is shared between calls; top-level const/let/class are wrapped in an IIFE. If/else blocks may return undefined — use a ternary or an explicit return.

NameTypeReqDescription
await_promisebooleanWhether to await Promise results
expressionstringyesJavaScript code to execute in the page context

No output schema declared.

No examples provided.

file_upload ~91

Upload file(s) to an <input type='file'> identified by ref or CSS selector; file paths must be absolute.

NameTypeReqDescription
pathyesAbsolute path(s) of the file(s) to upload
refstringElement ref of the file input
selectorstringCSS selector of the file input; needed for hidden inputs (display:none, off-screen), which have no ref

No output schema declared.

No examples provided.

fill_form ~82

Fill a whole form in one call: text inputs, <select> (by value or visible label), checkboxes (boolean) and radio buttons. One round-trip; partial errors do not abort and each field reports its own status. On per-field errors call view_page and retry the failing fields.

NameTypeReqDescription
fieldsarrayyesEach needs ref or selector plus value

No output schema declared.

No examples provided.

handle_dialog ~82

Configure handling of alerts, confirms and prompts. Set it BEFORE triggering the action that opens the dialog. Uses CDP Page.javascriptDialogOpening, so it works even while the dialog blocks all JS.

NameTypeReqDescription
actionstringyesaccept or dismiss the next dialog; get_status: pending ones
textstringText entered into prompt dialogs (with action accept)

No output schema declared.

No examples provided.

navigate ~109

Navigate the active tab to a URL, or action 'back' / 'reload' (all refs become stale after reload). Waits for settle. Overwrites the user's active tab — check virtual_desk first; the first call per session is redirected to virtual_desk.

NameTypeReqDescription
actionstringgoto (default) | back | reload
settle_msnumberExtra wait in ms after load (default 500)
urlstringURL to open (required for goto)

No output schema declared.

No examples provided.

network_monitor ~83

Capture network requests via CDP, including those the page issues itself. Workflow: start → trigger the action → get(pattern: 'api').

NameTypeReqDescription
actionstringyesstart recording | get results | stop: return and clear
filterstring'failed': only HTTP >= 400 or network errors
patternstringRegex for request URLs

No output schema declared.

No examples provided.

observe ~217

Watch an element for changes instead of polling with MutationObserver/setInterval code in evaluate. collect: record text/attribute changes for 'duration' ms. until: wait for a condition, then optionally click at once (then_click). click_first fires the triggering action after the observer is armed, so nothing is missed.

NameTypeReqDescription
click_firststringSelector or ref to click once the observer is armed
collectstringtext (textContent) | attributes | all
durationnumberCollect window in ms (default 5000); exclusive with until
intervalnumberPolling fallback interval in ms
selectorstringyesCSS selector or ref of the element to observe
then_clickstringSelector or ref to click immediately when until holds
timeoutnumberMax observation time in ms (max 25000)
untilstringJS expression checked on each change, 'el' is the element, e.g. el.textContent === '8'

No output schema declared.

No examples provided.

press_key ~95

Press a key or shortcut (Enter, Escape, Tab, arrows, Ctrl+K). Optionally focus an element first via ref or selector.

NameTypeReqDescription
keystringyesKey to press, e.g. 'Enter'; printable chars as-is
modifiersarrayModifier keys held during the press
refstringElement ref to focus first
selectorstringCSS selector to focus first

No output schema declared.

No examples provided.

run_plan ~195

Batch the next 2+ known actions (click, type, scroll, view_page chains) here instead of N separate calls: a sequence of tool steps, executed server-side in one call. Variables via vars and saveAs ($name), conditions (if), suspend/resume to ask the agent mid-plan, errorStrategy abort | continue | capture_image, and parallel groups per tab: parallel: [{ tab, steps }].

NameTypeReqDescription
errorStrategystringabort stops at the first error; continue runs all steps; capture_image screenshots, then aborts
parallelarrayTab groups to run in parallel
resumeobjectResume a suspended plan
stepsarrayTool steps to run in order
use_operatorbooleanOperator mode (rule engine + micro-LLM); needs the executeOperator hook
varsobjectInitial variables, available as $name

No output schema declared.

No examples provided.

scroll ~151

Scroll the page, a container, or an element into view. Reports the position and content growth (scrollHeight delta — detects lazy-loaded content) and handles settle timing. Use container_ref/container_selector plus direction to scroll inside a container.

NameTypeReqDescription
amountnumberPixels per scroll (default 500); only with direction
container_refstringScrollable container ref (scrolls it, not the page)
container_selectorstringScrollable container CSS selector
directionstringup or down (default down); used when no ref/selector
refstringElement ref to scroll into view
selectorstringCSS selector to scroll into view

No output schema declared.

No examples provided.

set_page_data ~219

Write a payload larger than 1 MB into window.__pb_data[key], chunked past the CDP 1 MB message limit. Source: inline (`data`) or file (absolute `path`, read as binary). The page reads window.__pb_data[key] (string or ArrayBuffer per encoding) and window.__pb_data[key + '__complete'] === true. Never write one key from parallel calls — they race. Under ~200 KB use evaluate; for a real <input type=file> use file_upload.

NameTypeReqDescription
chunkSizeintegerRaw bytes per chunk before base64 (default 500000; max 700000)
encodingstringutf8 (inline default) keeps a string; binary (file default) gives an ArrayBuffer for FileReader/Blob/fetch; base64 keeps the base64 string
keystringyesProperty name under window.__pb_data (JS identifier, see pattern)
sourceyesinline: pass data. file: pass an absolute path, read as binary

No output schema declared.

No examples provided.

switch_tab ~114

Open a new tab, switch to a tab by ID (from virtual_desk), or close one. Prefer 'open' over navigate when the user's active tab must stay untouched. Refs from the previous tab are invalid afterwards — call view_page before acting.

NameTypeReqDescription
actionstringopen | switch | close
tabstringTab ID or 1-based number (switch/close; close: active tab)
urlstringURL for a new tab (open); default about:blank

No output schema declared.

No examples provided.

tab_status ~43

Active tab's cached URL, title, ready state and errors — a cheap mid-workflow sanity check ('did my click navigate?'). Not for tab discovery or page content.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

type ~94

Type text into an input identified by ref or CSS selector. For 2+ fields use fill_form; for special keys (Enter, Escape, Tab, arrows) or shortcuts (Ctrl+K) use press_key.

NameTypeReqDescription
clearbooleanClear the field first
refstringElement ref (preferred)
selectorstringCSS selector (fallback)
textstringyesText to type

No output schema declared.

No examples provided.

view_page ~153

See what is on the page: text plus stable element refs for click/type/fill_form. Default filter 'interactive' lists actionable elements; for paragraphs or table cells call view_page(ref, filter: 'all'). Collapsed containers show as [eXX role, N items] — expand with view_page(ref: 'eXX', filter: 'all').

NameTypeReqDescription
depthnumberTree levels shown; indentation only, hidden sections need a click
filterstringinteractive | all | landmark | visual (bounds, click point, visibility)
max_tokensintegerToken budget; content downsampled. Omit for full output
refstringElement ref for a subtree

No output schema declared.

No examples provided.

virtual_desk ~51

List all open tabs with IDs, URLs and state. Call it first in every session, after a reconnect, or when unsure; reuse a listed tab ID instead of opening duplicates. Cheap, call liberally.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

wait_for ~207

Wait until a condition holds: element visible, page text present, URL match, network idle, or a JS expression true. Prefer condition 'text' over a JS expression for 'has the page said X yet'. assert: true checks once and fails instead of waiting.

NameTypeReqDescription
assertbooleanCheck once, fail if it does not hold; timeout 0, _meta.code 'assertion_failed'
conditionstringyeselement | text | url | network_idle | js
expressionstringExpression that should become true; required for condition 'js'
selectorstringCSS selector or ref; required for condition 'element'
textstringSubstring of document.body.innerText, case-sensitive; required for condition 'text'
timeoutnumberMax wait in ms (default 10000; 0 when assert is true)
urlstringSubstring of the page URL; required for condition 'url'

No output schema declared.

No examples provided.

Common questions

What is the Public Browser MCP server?

Public Browser is an MCP server listed in the public MCP registry as io.github.Silbercue/public-browser. Browse your real profile: -30% tokens, -25% cost, -41% tool calls, -34% tool defs, +40% faster. This page covers its npm package (public-browser).

Is the Public Browser MCP server safe to use?

Public Browser scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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 Public Browser MCP server expose?

Public Browser exposes 25 tools: virtual_desk, view_page, click, type, fill_form, and 20 more. Their descriptions and schemas cost roughly 3,155 tokens of context every time the server is loaded.

Is the Public Browser MCP server still maintained?

Public Browser is still listed as active in the MCP registry. We last reached this channel on 20 September 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 Public Browser MCP server under?

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