Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
Poltertab is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
28
downloads a day
local
runs on your machine
4k
downloads in 30d
What it does
Drive and scrape your existing Chrome profile from any AI assistant — no headless browser.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user poltertab-mcp '--' npx -y poltertab
# 2 — ask your agent for something these tools do
# browser_navigate, browser_click, browser_fill and 25 more
Poltertab costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ABAll 1 server
abhinav1621 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Poltertab as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user poltertab-mcp '--' npx -y poltertabReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
28 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Navigate to any URL in the browser
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Click an element on the page. Returns the element's fingerprint (pass it back later to survive a selector change) and healed:true if the selector had drifted and the element was relocated.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | — |
Fill an input field with text. Returns the field's fingerprint (pass it back later to survive a selector change) and healed:true if the selector had drifted and the field was relocated.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | — |
| value | string | yes | — |
| submit | boolean | no | — |
Scrape the page or specific elements. For repeating records (cards, rows, listings) use browser_extract instead — it keeps fields grouped per record.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | no | — |
| attribute | string | no | Attribute to read, or 'text' for the element's text. 'href'/'src' come back absolute. |
| multiple | boolean | no | — |
| fields | array | no | Full-page scrape only (no selector): which parts to return. title and url are always included. ['meta','jsonld'] is the cheap structured-data path — og: tags and schema.org blobs without 50KB of body |
| max_text | number | no | Max characters of text per element (default 500) |
Extract repeating records (cards, rows, listings) with fields grouped per record. Fields resolve INSIDE each record root and a missing field yields null instead of shifting later records' values. Returns fill rates and warns when a field is empty inside the record scope but matches page-wide…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| record | string | no | Selector for the repeating container, e.g. '.agent-card'. Verify with browser_snapshot that it encloses ALL the fields you want — the element that looks like the card often excludes siblings holding s |
| fields | object | no | Map of field name -> {sel, get, many, strip}. sel is relative to the record root; omit it (or use '.') for the root itself. get: 'text' (default) | 'href' | 'src' | any attribute name. many: true coll |
| anchor | string | no | Name of the field that is always present on a real record (usually the detail-page link). Records missing it are dropped as placeholders and counted in 'dropped'. |
| max_text | number | no | Max characters per text field (default 500) |
| probe | boolean | no | Page-wide re-check of any field that came back entirely empty (default true) |
Paginate and extract in one call, with no model round-trip per page. Takes browser_extract's spec plus a URL template — the spec is optional when a recipe was learned for that page shape, and a recipe learned here stores the template so a later call can replay both. Walks pages, dedups on a key,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url_template | string | yes | URL with a {page} placeholder, e.g. 'https://www.kw.com/agents?page={page}' |
| record | string | no | — |
| fields | object | no | — |
| anchor | string | no | — |
| key | string | no | Field name to dedup on — use a stable per-record identifier such as the detail URL. Falls back to whole-row equality. |
| limit | number | no | Stop after this many records (default 200) |
| offset | number | no | Skip this many records from the start of the stream. Pages are re-fetched to reach the offset; pass start_page to skip cheaply. |
| start_page | number | no | First page (default 1) |
| max_pages | number | no | Hard guard on pages fetched (default 50) |
| fill_tolerance | number | no | Halt when a field well-populated on the baseline page falls below this fraction of it (default 0.5). 0 disables the check. |
| max_text | number | no | — |
| session | no | — |
Capture visible tab as base64 PNG. This action will focus the target tab.
No parameter schema on file.
Scroll the page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| direction | string | yes | — |
| amount | number | no | — |
| selector | string | no | — |
Hover over an element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | — |
Get text content of an element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | — |
| max_text | number | no | Max characters (default 10000). The result flags it when text was cut. |
Get page title and URL
No parameter schema on file.
Get page URL
No parameter schema on file.
Get a snapshot of the DOM. Large pages run to tens of KB — narrow it with interactive_only/max_nodes, or send it to output_file, before spending the context on it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| interactive_only | boolean | no | Only clickable/typable elements |
| max_nodes | number | no | Cap on nodes returned (default 400) |
| max_depth | number | no | — |
Get captured raw JSON data (GraphQL/XHR) for the current tab, bypassing DOM virtualization
| Parameter | Type | Required | Notes |
|---|---|---|---|
| clear | boolean | no | Clear the buffer after reading (default: true) |
Set URL substrings to determine which network requests are captured in the MAIN world.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| patterns | array | yes | Array of substrings (e.g. ['graphql', '/api/v1/comments']) |
Scroll the page and wait for new network data to load (handles lazy-loading)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| direction | string | yes | — |
| amount | number | no | — |
Create or track a named browser session (tab): opens url in a new tab, adopts tabId, or with neither binds the tab the user is looking at. It becomes the current tab.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| url | string | no | — |
| tabId | number | no | Adopt this already-open tab instead of opening one |
Switch to a different tracked session
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
List all tracked sessions
No parameter schema on file.
Close a tracked session and its tab. Tabs not opened by PolterTab — including ones adopted via browser_session_create({tabId}) — require the user's permission: the tool returns code needs_user_permission with the tab's id, title and url; ask the user, then retry with force: true.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| force | boolean | no | Close a tab the user opened. Only when the user asked. |
Get this agent's current tab: its id, URL, title and session name, or closedTabId if the tab it was on has been closed
No parameter schema on file.
Open a new tab and make it this agent's current tab. Later calls without tabId/session act on it. Returns its tabId.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | no | Page to open; blank tab if omitted |
| session | string | no | Also name the tab as a session, to come back to it by name |
| background | boolean | no | Open without stealing focus from the user's tab |
List the tabs this agent can work with: every tab PolterTab opened or bound to a session, marking which one is current. all: true lists every open tab in the browser (ids, URLs and titles only).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| all | boolean | no | Include the user's other tabs |
Make another tab this agent's current tab, by tabId or session name. Does not bring it to the front unless focus: true.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | number | no | Tab to switch to; a tabId Chrome does not have returns tab_not_found |
| session | string | no | — |
| focus | boolean | no | Also show the tab to the user |
Close a tab by tabId or session name (default: the current tab). Tabs not opened by PolterTab — including ones adopted via browser_session_create({tabId}) — require the user's permission: the tool returns code needs_user_permission with the tab's id, title and url; ask the user, then retry with…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | number | no | — |
| session | string | no | — |
| force | boolean | no | Close a tab the user opened. Only when the user asked. |
Get navigation memory for a website domain: the obstacles and fixes saved for it, plus any extraction recipes learned there — their fields, their variants, and the steps that were observed before each one worked. The steps are observations, not a script: reissue one only if it still fits the page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hostname | string | no | e.g., 'www.linkedin.com' or 'x.com' |
| domain | string | no | Alias for hostname |
Save a new navigation memory, obstacle, or fix for a specific website domain
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hostname | string | no | e.g., 'www.linkedin.com' |
| domain | string | no | Alias for hostname |
| obstacle | string | yes | What broke or was difficult? |
| solution | string | yes | How did you solve it? |
Upload one or more local files to the current page. Works with plain file inputs (visible or hidden), custom upload buttons, shadow-DOM inputs (open roots only, one level deep), top-level same-origin iframes, and drag-and-drop zones. For file inputs and upload buttons, uses CDP (Chrome DevTools…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | CSS selector for the upload trigger — the visible button, label, or file input itself. For drop zones (method: 'drop'), the selector of the drop target element. |
| paths | array | yes | Absolute paths to local files to upload. Each must be within a directory listed in upload_allowed_paths in ~/.poltertab/config.json. |
| method | string | no | 'picker' (default): click the selector and intercept the OS file chooser via CDP — works for any file input or button that opens one. 'drop': dispatch drag-and-drop events with the file bytes — use fo |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under ISC
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Poltertab or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 1.12.0 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings1 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digeste976a8e65a7d1275a7b4ed5e574ea1eab7be41172ddf52d463a0ca51fdd1e2cf
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digeste976a8e65a7d1275
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.12.0. Pin a release below and the command asks for exactly that one.
1.12.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Poltertab can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.