Stealthy browser automation, testing, and web-scraping via CDP Mode.
Nothing to run from here
Browser Control MCP by Nova (CIVAI) 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.
90/100
tool-list score
24
tools declared
remote
at its publisher
—
calls last 7d
What it does
Control your Chrome from chat: open websites, read what's on the page, click buttons, and fill in f…
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http browser-control-mcp-by-nova-civai https://nova.civai.co/mcp/agents/mcp-browsergpt-browser-control
# 2 — ask your agent for something these tools do
# set_browsergpt_license, list_browsers, ensure_remote_runner and 21 more
Browser Control MCP by Nova (CIVAI) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CIAll 47 servers
civai47 servers
19 categories
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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http browser-control-mcp-by-nova-civai https://nova.civai.co/mcp/agents/mcp-browsergpt-browser-controlReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
24 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.
Save BrowserGPT license when MCP headers did not already provide it (Authorization Bearer license). Optional when Nova/SecOps derived license from auth. Call before list_browsers only if license_not_set.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| license_key | string | yes | BrowserGPT license key |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
List BrowserGPT browser nodes (local + remote) for the configured license.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Start/prepare Nova remote BrowserGPT runner (ensure-remote-browser). Call when list_browsers shows no online+ready remote node; then list_browsers again.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Open MCP control session on target browser node_id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | yes | node_id from list_browsers |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
List tabs in the open control session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Accessibility snapshot with refs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | From browser_navigate or browser_tabs |
| interactive_only | boolean | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
JPEG screenshot of the session viewport.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | From browser_navigate or browser_tabs |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Navigate a tab to URL. Pass tab_id from browser_tabs to reuse an existing tab; omit or leave empty to use the active control tab. Returns tab_id in results[0].tab_id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| tab_id | string | no | Optional. browser_tabs targetId to navigate in place. |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Read session data for a tab via BrowserGPT extension: chrome.cookies (HttpOnly), optional localStorage/sessionStorage keys. Operator must approve the in-tab permission prompt. Use for session export / porting auth; do not paste values into chat.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | browser_tabs targetId |
| cookie_domains | array | yes | Domains for chrome.cookies.getAll (e.g. [".x.com", "x.com"]). Required. |
| cookie_names | array | no | Optional name filter |
| local_storage_keys | array | no | Optional localStorage key names to read on the target tab |
| session_storage_keys | array | no | Optional sessionStorage key names to read on the target tab |
| confirmation_message | string | yes | Plain-language permission prompt for the operator (no secrets or template syntax). |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Run JavaScript on a target tab (same CDP evaluate path as BrowserGPT Quick Task exec_js). Requires tab_id from browser_tabs. Returns ok, value, logs, metrics.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | browser_tabs targetId |
| javascript | string | yes | JavaScript source to evaluate |
| timeout_ms | integer | no | Default 15000, max 120000 |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Low-level action batch (JSON array string). Pass tab_id when batch includes switch_tab, close_tab, mouse_click, scroll, or keys.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| actions_json | string | yes | — |
| tab_id | string | no | Control context tab; required for switch_tab/close_tab batches |
| timeout_ms | integer | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Interact via snapshot ref.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| op | string | yes | — |
| ref | string | yes | — |
| text | string | no | — |
| key | string | no | — |
| code | string | no | — |
| input_method | string | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
List BrowserGPT dom input method ids; optional page_url for domain-specific hint.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page_url | string | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Click by snapshot ref (Cursor parity). Snapshot first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| ref | string | yes | — |
| element | string | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Fill field by ref.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| ref | string | yes | — |
| value | string | yes | — |
| input_method | string | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Type into field by ref.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| ref | string | yes | — |
| text | string | yes | — |
| slowly | boolean | no | — |
| input_method | string | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Press keyboard key in tab.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| key | string | yes | — |
| code | string | no | — |
| modifiers_json | string | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Scroll wheel; optional ref scrolls element into view first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| ref | string | no | — |
| deltaX | number | no | — |
| deltaY | number | no | — |
| amount | number | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Select options on a select ref.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| ref | string | yes | — |
| values_json | string | yes | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Drag between viewport coordinates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| startX | number | yes | — |
| startY | number | yes | — |
| endX | number | yes | — |
| endY | number | yes | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Click at viewport x/y when snapshot refs are empty.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| x | number | yes | — |
| y | number | yes | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Get ref bounding box from last snapshot.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| ref | string | yes | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Briefly outline ref on page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| ref | string | yes | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Run dom input method chain (e.g. 2,7,0); use after list_input_methods on stubborn fields.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tab_id | string | yes | — |
| text | string | yes | — |
| selector | string | no | — |
| method | string | no | — |
| input_method | string | no | — |
| notification_message | string | no | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Browser Control MCP by Nova (CIVAI) 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: —
ATool-list grade · score 90 / 100
Release 1.0.0 · scanned 3 Nov 2026
Graded from the tools this server lists, not from its source code.
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 score90
Findings0 threat · 2 capability
Capabilityhigh
Coveragemanifest
Verificationnot in this report
Surface digest3d11f5feffeca071f67f760bb5f3af8b424de957cc4449f51f5fe8e03c0d7a77
Score vectorthreat 100 → client 90
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| set_browsergpt_license | no tags | |
| list_browsers | no tags | |
| ensure_remote_runner | no tags | |
| open_control_session | no tags | |
| browser_tabs | no tags | |
| browser_snapshot | no tags | |
| browser_screenshot | no tags | |
| browser_navigate | no tags | |
| browser_get_cookies | no tags | |
| browser_exec_js | code-exec | code-exec: keyword "exec" in tool name |
| browser_actions | no tags | |
| browser_interact | no tags | |
| list_input_methods | no tags | |
| browser_click | no tags | |
| browser_fill | no tags | |
| browser_type | no tags | |
| browser_press_key | no tags | |
| browser_scroll | no tags | |
| browser_select_option | no tags | |
| browser_drag | no tags | |
| browser_mouse_click_xy | no tags | |
| browser_get_bounding_box | no tags | |
| browser_highlight | no tags | |
| browser_dom_input | no tags |
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 digest3d11f5feffeca071
Scanned2026-11-03
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
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 Browser Control MCP by Nova (CIVAI) 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.