io.github.abhinav162/poltertab
NPM · POLTERTAB
Drive and scrape your existing Chrome profile from any AI assistant — no headless browser.
Available components
Last scanned (19 hours ago)
Scores higher than 73% of npm servers
Category Browser Automation
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
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to abhinav162/poltertab). View diagnostics → Pass
- Clear OSI-approved license (ISC).Pass
- Actively maintained (last published 8 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 5303 tokens (~189/item across 28 items; 28 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 Management33
- Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 77% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 28 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 28 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
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.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 27 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 78
First indexed and scored.
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 4 Nov 2026 · Analysed npm/poltertab@1.12.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | abhinav162/poltertab |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/abhinav162/poltertab/.github/workflows/publish.yml@refs/tags/v1.12.0 |
| Rekor log index | 3462281529 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:2ce8c5fed4563656453033de2933e3138605d1a294f735bf5cf2ed764481b8cf9ad1e8a3f969472b35009888fea71ba883a96a3b8747c4959aed83d7b |
Background: How many MCP packages publish verified provenance →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
browser_click ~220
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.
| Name | Type | Req | Description |
|---|---|---|---|
| fingerprint | object | – | Optional. The `fingerprint` object a previous browser_click/browser_fill returned for this element. When the selector no longer matches, the element is relocated by structural similarity and the resu… |
| selector | string | yes | – |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_extract ~728
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 (record boundary too narrow). `record` and `fields` are optional when a recipe has already been learned for this page shape: omit them to replay it, and the result names it in `used_recipe` (with `stale: true` if the page no longer matches what was learned). `remember` names what a fresh spec is stored as.
| Name | Type | Req | Description |
|---|---|---|---|
| anchor | string | – | 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'. |
| fields | object | – | 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 col… |
| max_text | number | – | Max characters per text field (default 500) |
| output_file | string | – | Filename to write the payload under ~/.poltertab/downloads/, returning only a summary (row count, field names, fill rates, two sample records). .jsonl and .csv are written in those formats when the p… |
| probe | boolean | – | Page-wide re-check of any field that came back entirely empty (default true) |
| recipe | string | – | Name of a learned recipe to replay. Only needed when more than one has been learned for this page shape — with exactly one, omitting `record`/`fields` uses it. browser_navigate lists what exists in `… |
| record | string | – | 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… |
| remember | string | – | Name this extraction so it can be replayed later, as 'name' or 'name/variant'. Optional: a spec that produced clean rows is remembered anyway, under a name derived from its fields and a variant deriv… |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
| variant | string | – | Which slice of the recipe to replay (a filter combination it was learned under). Only needed when the recipe has more than one. Variant names are derived from the steps that preceded the extract, so… |
No output schema declared.
No examples provided.
browser_extract_all ~672
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, and halts on: limit reached, empty page, a page whose records repeat an earlier page's (the trap where ignored page-size params silently return page 1 again), fill rates collapsing against page 1's baseline, or max_pages. Always reports which condition fired and returns everything collected so far.
| Name | Type | Req | Description |
|---|---|---|---|
| anchor | string | – | – |
| fields | object | – | – |
| fill_tolerance | number | – | Halt when a field well-populated on the baseline page falls below this fraction of it (default 0.5). 0 disables the check. |
| key | string | – | Field name to dedup on — use a stable per-record identifier such as the detail URL. Falls back to whole-row equality. |
| limit | number | – | Stop after this many records (default 200) |
| max_pages | number | – | Hard guard on pages fetched (default 50) |
| max_text | number | – | – |
| offset | number | – | Skip this many records from the start of the stream. Pages are re-fetched to reach the offset; pass start_page to skip cheaply. |
| output_file | string | – | Filename to write the payload under ~/.poltertab/downloads/, returning only a summary (row count, field names, fill rates, two sample records). .jsonl and .csv are written in those formats when the p… |
| recipe | string | – | Name of a learned recipe to replay. Only needed when more than one has been learned for this page shape — with exactly one, omitting `record`/`fields` uses it. browser_navigate lists what exists in `… |
| record | string | – | – |
| remember | string | – | Name this extraction so it can be replayed later, as 'name' or 'name/variant'. Optional: a spec that produced clean rows is remembered anyway, under a name derived from its fields and a variant deriv… |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| start_page | number | – | First page (default 1) |
| url_template | string | yes | URL with a {page} placeholder, e.g. 'https://www.kw.com/agents?page={page}' |
| variant | string | – | Which slice of the recipe to replay (a filter combination it was learned under). Only needed when the recipe has more than one. Variant names are derived from the steps that preceded the extract, so… |
No output schema declared.
No examples provided.
browser_fill ~234
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.
| Name | Type | Req | Description |
|---|---|---|---|
| fingerprint | object | – | Optional. The `fingerprint` object a previous browser_click/browser_fill returned for this element. When the selector no longer matches, the element is relocated by structural similarity and the resu… |
| selector | string | yes | – |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| submit | boolean | – | – |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
| value | string | yes | – |
No output schema declared.
No examples provided.
browser_get_network_state ~236
Get captured raw JSON data (GraphQL/XHR) for the current tab, bypassing DOM virtualization
| Name | Type | Req | Description |
|---|---|---|---|
| clear | boolean | – | Clear the buffer after reading (default: true) |
| output_file | string | – | Filename to write the payload under ~/.poltertab/downloads/, returning only a summary (row count, field names, fill rates, two sample records). .jsonl and .csv are written in those formats when the p… |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_get_site_memory ~99
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.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | – | Alias for hostname |
| hostname | string | – | e.g., 'www.linkedin.com' or 'x.com' |
No output schema declared.
No examples provided.
browser_get_text ~236
Get text content of an element
| Name | Type | Req | Description |
|---|---|---|---|
| max_text | number | – | Max characters (default 10000). The result flags it when text was cut. |
| output_file | string | – | Filename to write the payload under ~/.poltertab/downloads/, returning only a summary (row count, field names, fill rates, two sample records). .jsonl and .csv are written in those formats when the p… |
| selector | string | yes | – |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_get_title ~130
Get page title and URL
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_get_url ~128
Get page URL
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_hover ~135
Hover over an element
| Name | Type | Req | Description |
|---|---|---|---|
| selector | string | yes | – |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_navigate ~139
Navigate to any URL in the browser
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
| url | string | yes | – |
No output schema declared.
No examples provided.
browser_save_site_memory ~74
Save a new navigation memory, obstacle, or fix for a specific website domain
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | – | Alias for hostname |
| hostname | string | – | e.g., 'www.linkedin.com' |
| obstacle | string | yes | What broke or was difficult? |
| solution | string | yes | How did you solve it? |
No output schema declared.
No examples provided.
browser_scrape ~349
Scrape the page or specific elements. For repeating records (cards, rows, listings) use browser_extract instead — it keeps fields grouped per record.
| Name | Type | Req | Description |
|---|---|---|---|
| attribute | string | – | Attribute to read, or 'text' for the element's text. 'href'/'src' come back absolute. |
| fields | array | – | 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 | – | Max characters of text per element (default 500) |
| multiple | boolean | – | – |
| output_file | string | – | Filename to write the payload under ~/.poltertab/downloads/, returning only a summary (row count, field names, fill rates, two sample records). .jsonl and .csv are written in those formats when the p… |
| selector | string | – | – |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_screenshot ~140
Capture visible tab as base64 PNG. This action will focus the target tab.
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_scroll ~148
Scroll the page
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | – | – |
| direction | string | yes | – |
| selector | string | – | – |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_session_close ~96
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.
| Name | Type | Req | Description |
|---|---|---|---|
| force | boolean | – | Close a tab the user opened. Only when the user asked. |
| name | string | yes | – |
No output schema declared.
No examples provided.
browser_session_context ~40
Get this agent's current tab: its id, URL, title and session name, or closedTabId if the tab it was on has been closed
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
browser_session_create ~82
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.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
| tabId | number | – | Adopt this already-open tab instead of opening one |
| url | string | – | – |
No output schema declared.
No examples provided.
browser_session_list ~14
List all tracked sessions
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
browser_session_switch ~23
Switch to a different tracked session
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
No output schema declared.
No examples provided.
browser_set_intercept_patterns ~165
Set URL substrings to determine which network requests are captured in the MAIN world.
| Name | Type | Req | Description |
|---|---|---|---|
| patterns | array | yes | Array of substrings (e.g. ['graphql', '/api/v1/comments']) |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_smart_scroll ~155
Scroll the page and wait for new network data to load (handles lazy-loading)
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | – | – |
| direction | string | yes | – |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_snapshot ~272
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.
| Name | Type | Req | Description |
|---|---|---|---|
| interactive_only | boolean | – | Only clickable/typable elements |
| max_depth | number | – | – |
| max_nodes | number | – | Cap on nodes returned (default 400) |
| output_file | string | – | Filename to write the payload under ~/.poltertab/downloads/, returning only a summary (row count, field names, fill rates, two sample records). .jsonl and .csv are written in those formats when the p… |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
browser_tab_close ~147
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 force: true. A tabId that does not exist in Chrome returns tab_not_found. Closing the current tab leaves no current tab; untargeted calls then error until you switch or navigate.
| Name | Type | Req | Description |
|---|---|---|---|
| force | boolean | – | Close a tab the user opened. Only when the user asked. |
| session | string | – | – |
| tabId | number | – | – |
No output schema declared.
No examples provided.
browser_tab_list ~66
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).
| Name | Type | Req | Description |
|---|---|---|---|
| all | boolean | – | Include the user's other tabs |
No output schema declared.
No examples provided.
browser_tab_new ~89
Open a new tab and make it this agent's current tab. Later calls without tabId/session act on it. Returns its tabId.
| Name | Type | Req | Description |
|---|---|---|---|
| background | boolean | – | Open without stealing focus from the user's tab |
| session | string | – | Also name the tab as a session, to come back to it by name |
| url | string | – | Page to open; blank tab if omitted |
No output schema declared.
No examples provided.
browser_tab_switch ~82
Make another tab this agent's current tab, by tabId or session name. Does not bring it to the front unless focus: true.
| Name | Type | Req | Description |
|---|---|---|---|
| focus | boolean | – | Also show the tab to the user |
| session | string | – | – |
| tabId | number | – | Tab to switch to; a tabId Chrome does not have returns tab_not_found |
No output schema declared.
No examples provided.
browser_upload_file ~404
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 Protocol) to intercept the OS file picker — a brief debugging banner appears during the upload. For drop zones, dispatches a DataTransfer drag-and-drop event. Paths must be within directories configured in upload_allowed_paths in ~/.poltertab/config.json. Nested iframes (iframe inside iframe) and cross-origin (out-of-process) iframes are not supported and return a clear error.
| Name | Type | Req | Description |
|---|---|---|---|
| method | string | – | '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 f… |
| 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. |
| 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. |
| session | string | – | Named session (tab) to run against; it becomes the current tab. browser_navigate with a new name opens it its own tab, so a loop can keep one tab instead of opening hundreds. Other tools error on a n… |
| tabId | number | – | Act on this tab (an id from browser_tab_list) without making it current. Omit to use this agent's current tab: the last one navigated, opened or switched to. A tabId Chrome does not have returns tab_… |
No output schema declared.
No examples provided.
How do I install the io.github.abhinav162/poltertab MCP server?
io.github.abhinav162/poltertab runs locally as an npm package, launched with npx -y poltertab. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · poltertab
claude mcp add abhinav162-poltertab -- npx -y poltertab
What is the io.github.abhinav162/poltertab MCP server?
io.github.abhinav162/poltertab is an MCP server listed in the public MCP registry as io.github.abhinav162/poltertab. Drive and scrape your existing Chrome profile from any AI assistant, no headless browser. This page covers its npm package (poltertab).
Is the io.github.abhinav162/poltertab MCP server safe to use?
io.github.abhinav162/poltertab scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 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 io.github.abhinav162/poltertab MCP server expose?
io.github.abhinav162/poltertab exposes 28 tools: browser_navigate, browser_click, browser_fill, browser_scrape, browser_extract, and 23 more. Their descriptions and schemas cost roughly 5,303 tokens of context every time the server is loaded.
Is the io.github.abhinav162/poltertab MCP server still maintained?
io.github.abhinav162/poltertab is still listed as active in the MCP registry. We last reached this channel on 4 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 io.github.abhinav162/poltertab MCP server under?
io.github.abhinav162/poltertab declares the ISC licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.