Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
Snapsurf 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.
93/100
trust score
12
downloads a day
local
runs on your machine
329
downloads in 30d
What it does
Web navigation and verification for AI agents: page digest, typed diff per action, assertions.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user snapsurf-mcp '--' npx -y @zumer/snapsurf
# 2 — ask your agent for something these tools do
# browser_open, browser_find, browser_parent and 12 more
Snapsurf costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
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 Snapsurf 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 snapsurf-mcp '--' npx -y @zumer/snapsurfReconnect, 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
15 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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
| waitForChallenge | number | no | ms to wait for a bot-mitigation interstitial to clear by itself (capped at 30000). Many do within a few seconds. Omitted = do not wait, just report. |
| digest | string | no | compact = the extraction profile: no bbox, no section, and the prose collapses to one line because the digest is already in structuredContent. Halves the per-page cost for a sweep that reads fields an |
| url | string | yes | URL (https implied; file:/data: accepted) |
| redact | array | no | Session privacy rules: strings to redact from every observation from now on (replaces any previous rules) |
Search text across the WHOLE page (not just the visible part) and get RANKED matches in structuredContent: id, role, name, text (same string, honest label), href (mailto:/tel: pass through intact) and truncated when a value was cut. Optional contextChars allocates a TOTAL text budget…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
| text | string | yes | — |
| contextChars | number | no | Optional TOTAL context budget across ranked matches, integer 1–12000 characters. Omitted keeps compact matches. |
Climb from a find/digest match to the CARD around it (the nearest container with ≥2 actionables) and observe just that subtree: the way from "found the price text" to "here is the clickable title next to it". Returns the card with fresh ids; the global look baseline stays untouched. When the card…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
| id | string | yes | id of the inner node (from find/digest/map) |
Act on the page: click (by id from the digest/find, or "x,y"), type (into the focused element — click it first), or enter. Click auto-scrolls and CONFIRMS role/name of the resolved element: read that echo before continuing. After acting, call browser_verify.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | click REQUIRES target; type REQUIRES text; enter needs neither |
| target | string | no | REQUIRED for click: id n_xxx from the digest/find, or "x,y" |
| text | string | no | REQUIRED for type: the text to type into the focused element |
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
WHAT CHANGED since the last observation — the verification of your action. Returns changed (a faithful negative: if your click did nothing it says so instead of letting you believe you acted), the list of changes with kind (added/removed/state/style/moved) role and name, and what became covered or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
Save the currently observed state as a NAMED baseline (before a risky action). NOT undo: a comparison point for browser_diff.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
| name | string | yes | — |
Diff the current state against a checkpoint saved with browser_checkpoint: everything that changed since that known point. Note: the next browser_verify baseline becomes the current state.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
| name | string | yes | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
| diffId | string | no | opaque evidence id from browser_verify: assert that stored full transition without observing; accepts only diff predicates, never live page checks or retry/ignore/baseline options |
| url | string | no | live mode only: substring the current URL must contain |
| changed | boolean | no | expected changed value for the stored diffId, or for the diff since the last observation in live mode |
| mustInclude | array | no | changes that must appear in the diff (selector = exact; to = expected state after, e.g. {expanded:true}) |
| mustNotInclude | array | no | changes that must NOT appear (assert absence of side-effects) |
| only | array | no | change scoping: EVERY change must match one of these matchers; this does not establish causality |
| ignore | array | no | live mode only: CSS selectors whose subtree changes are excluded (e.g. the agent toolbar) |
| maxChanges | number | no | full diff must contain at most N changes (after ignore in live mode) |
| becameVisible | string | no | an actionable matching this text must have become visible |
| becameCovered | string | no | an actionable matching this text must have become covered |
| settleMs | number | no | live mode only: wait before the first walk |
| retry | object | no | live mode only: re-walk against the SAME baseline until pass or budget |
| exists | string | no | live mode only: text that must be findable on the current page |
| notCovered | string | no | live mode only: text whose best match must not be occluded on the current page |
| keepBaseline | boolean | no | live mode only: do not consume the diff baseline (peek mode — safe to retry); incompatible with diffId even when false |
Scroll WITHOUT acting: by element id (to center), to "top"/"bottom", or to an absolute y in pixels. The one legitimate reason: dense listings hydrate their content lazily on scroll and the semantic walk honestly sees only the DOM that exists — scroll, then browser_verify to see what appeared. Ids…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | yes | id n_xxx, "top", "bottom", or a y offset in pixels |
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
Read visible text of ONE node or section by id, with a bounded character budget (maxChars defaults to 600, maximum 12000). Returns text, textSource, capturedAt (first-read timestamp), totalChars, returnedChars, offset, nextOffset, truncated, observationId and continuation in structuredContent.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
| id | string | yes | — |
| maxChars | number | no | Integer characters per slice, 1–12000; default 600. |
| offset | number | no | Integer start offset; default 0. Positive offsets require observationId and an initial read. |
| observationId | string | no | Observation owning the initial text read; required when offset > 0. |
Expanded views when the digest is not enough: outline (full structure trimmed to 12KB), map with offset (pages actionables beyond the top), or zoom with id (observes ONLY that subtree — the detail of a region/card; renews ids, global baseline untouched). Explicit escalation — digest first. Returns…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| view | string | yes | zoom REQUIRES id; map takes an optional offset |
| offset | number | no | map only: start index |
| id | string | no | REQUIRED for zoom: region/element id |
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
Open an independent browsing session and get its sessionId. Each session owns a private BrowserContext, cookie/storage jar, popup tree, observation counter and ids, so several sweeps run AT THE SAME TIME without invalidating or authenticating each other. Pass the returned sessionId on every call…
No parameter schema on file.
Close a session opened with browser_session_open and free its complete context, including every popup it created. Sessions also close themselves after 10 minutes idle, so a crashed run does not leak pages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | yes | — |
List the live sessions with their current URL, observation number and idle time.
No parameter schema on file.
Pixels as ESCALATION, not default: snapdom render of the viewport, or of one element (scrolled to center) when you pass an id. Only when the doubt is genuinely visual (layout, color, overlap) — for what changed there is browser_verify.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sessionId | string | no | optional: the session this call belongs to (from browser_session_open). Omitted uses the shared default session. |
| id | string | no | optional: element to center |
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 Snapsurf 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 93 / 100
Release 0.1.2 · scanned 15 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 score93
Findings5 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest2a67b0033254fb21e3007b3d5e6bbfda1c93c23bca6ea21d3b3b571173f77667
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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 (12 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| browser_open | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| browser_find | no tags | |
| browser_parent | no tags | |
| browser_verify | no tags | |
| browser_checkpoint | no tags | |
| browser_diff | no tags | |
| browser_scroll | no tags | |
| browser_text | no tags | |
| browser_session_open | state-write | state-write: declares readOnlyHint: false |
| browser_session_close | state-write | state-write: declares readOnlyHint: false |
| browser_session_list | no tags | |
| browser_screenshot | 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 digest2a67b0033254fb21
Scanned2026-10-15
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 0.1.2. Pin a release below and the command asks for exactly that one.
0.1.2
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 Snapsurf 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.