Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
Monkeysee Bridge 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.
95/100
trust score
5
downloads a day
local
runs on your machine
53
downloads in 30d
What it does
MCP server that lets an MCP client (Claude Code, Codex, any MCP client) drive a real, logged-in Chrome profile. Ships the MonkeySee Chrome extension bundled.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user monkeysee-bridge-mcp '--' npx -y monkeysee-bridge
# 2 — ask your agent for something these tools do
# get_state, screenshot, get_forms and 22 more
Monkeysee Bridge costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JUAll 1 server
juliocesar1 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 Monkeysee Bridge 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 monkeysee-bridge-mcp '--' npx -y monkeysee-bridgeReconnect, 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
25 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.
Observation: read the current page as an indexed list of visible elements with roles, names, and bounding boxes. This is your primary "look at the page". Returns a PageState. Pass withScreenshot:true to also get a viewport image with numbered marks at each element.
No parameter schema on file.
Observation: capture the controlled tab's visible viewport as a PNG image. Use when the indexed element list is not enough and you need to see the page.
No parameter schema on file.
Observation: read only the page's forms as a compact, grouped list of fields — kind, type, label, name, autocomplete, current value, checked state, select/radio options, and required/disabled flags. Covers native controls plus ARIA-role widgets and open shadow DOM. Each field's index is directly…
No parameter schema on file.
Observation: read the human-readable text of the page (or the subtree at the given element index). Use this when the task ends in reading content.
No parameter schema on file.
Semantic action (operates on an index from get_state): click the element at index.
No parameter schema on file.
Semantic action (operates on an index from get_state): choose value in the <select> at index.
No parameter schema on file.
Semantic action (operates on an index from get_state): fill multiple form fields in one call (the batch counterpart to get_forms). Pass an array of { index, value? | option? | checked? } using indices from get_forms: value types into a text/contenteditable field, option chooses a…
No parameter schema on file.
Semantic action (operates on an index from get_state): hover the element at index.
No parameter schema on file.
Semantic action (operates on an index from get_state): focus the element at index.
No parameter schema on file.
Spatial/raw action (CSS px, viewport-relative): click at viewport coordinates (x, y).
No parameter schema on file.
Spatial/raw action (CSS px, viewport-relative): scroll the page in a direction by an optional amount (default ~ one viewport).
No parameter schema on file.
Spatial/raw action (CSS px, viewport-relative): scroll the element at index into view.
No parameter schema on file.
Spatial/raw action (CSS px, viewport-relative): drag from (x1, y1) to (x2, y2).
No parameter schema on file.
Spatial/raw action (CSS px, viewport-relative): press a key (e.g. 'Enter', 'Tab', 'Escape') on the focused element, with optional modifiers.
No parameter schema on file.
Spatial/raw action (CSS px, viewport-relative): type text into the currently focused element, character by character.
No parameter schema on file.
Navigation / lifecycle: open a new tab at url and make it the controlled tab.
No parameter schema on file.
Tab management (multi-tab control): list all open tabs as { tabId, url, title, active, controlled }, plus the current controlledTabId. Use this to discover tabs to switch to or target via a tool's optional tabId.
No parameter schema on file.
Tab management (multi-tab control): make tabId the controlled tab (where default-target actions go) and bring it to the front.
No parameter schema on file.
Tab management (multi-tab control): close the tab with tabId. If it was the controlled tab, control falls back to the active tab on the next action.
No parameter schema on file.
Navigation / lifecycle: navigate the controlled tab to url.
No parameter schema on file.
Navigation / lifecycle: navigate the controlled tab back in history.
No parameter schema on file.
Navigation / lifecycle: navigate the controlled tab forward in history.
No parameter schema on file.
Navigation / lifecycle: wait until the controlled tab has finished navigating and the DOM has settled, or timeoutMs elapses (default 10s).
No parameter schema on file.
Control: declare the task complete with your answer. The bridge grounds it by attaching the current tab URL and a short page snippet.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- 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 Monkeysee Bridge 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 95 / 100
Release 0.5.0 · scanned 14 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 score99
Client score95
Findings2 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestd4fc2c2d9b61e2e26ba166f13e81674e435a8c4232b7e8edb4cf039cc89775f7
Score vectorthreat 99 → client 95
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (25 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_state | no tags | |
| screenshot | no tags | |
| get_forms | no tags | |
| extract_text | no tags | |
| click | no tags | |
| type | no tags | |
| select_option | no tags | |
| fill_fields | no tags | |
| hover | no tags | |
| focus | no tags | |
| click_at | no tags | |
| scroll | no tags | |
| scroll_to | no tags | |
| drag | no tags | |
| press | no tags | |
| type_text | no tags | |
| open_tab | no tags | |
| list_tabs | no tags | |
| switch_tab | no tags | |
| close_tab | no tags | |
| navigate | no tags | |
| go_back | no tags | |
| go_forward | no tags | |
| wait_for_load | no tags | |
| done | 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 digestd4fc2c2d9b61e2e2
Scanned2026-10-14
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 0.5.0. Pin a release below and the command asks for exactly that one.
0.5.0
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 Monkeysee Bridge 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.