Real-time web search, reasoning, and research through Perplexity's API
Nothing to run from here
Site Prompt 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
6
tools declared
local
runs on your machine
—
downloads a day
What it does
Point at any part of a website and get a prompt that rebuilds it 1:1, or see how it is made.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user site-prompt-mcp '--' npx -y site-prompt
# 2 — ask your agent for something these tools do
# site_read, site_prompt, site_pick and 3 more
Site Prompt costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JOAll 1 server
johntony11 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 Site Prompt 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 site-prompt-mcp '--' npx -y site-promptReconnect, 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 asks of you
Nothing is required, but it can take SITE_PROMPT_WAIT (Seconds pick mode waits inside one tool call (default 240). Set it below your client's tool timeout.), SITE_PROMPT_TELEMETRY (Set to 0 to turn off anonymous usage counts.) if you want to set them.
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
6 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.
Read a website so it can be rebuilt 1:1. Opens it in Chrome like a person (scrolls it, waits for it to settle, clicks away a cookie banner) and measures everything: the stack it was built with (framework, styling, motion libraries, host), every colour, type style, radius, shadow, blur and spacing…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | the page, e.g. https://linear.app or stripe.com/payments |
Finish the build prompt for a site already read with site_read: adds your visual notes per section and an overall paragraph, and rewrites ~/Documents/Site Prompts/<site>/PROMPT.md. Copies it to the clipboard and returns it in full, with a link to the file: show both to the person.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | the same url given to site_read |
| overall | string | no | one paragraph: the look and feel of the whole page |
| notes | object | no | section number → what the eye sees in it |
Let the person point at what they like on a website (a button, a line of type, an illustration, a section, any component) and get a prompt that builds exactly that. With url: opens the site with a picker toolbar (in the person's own Chrome if remote debugging is on at…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | no | the site to open (first call); omit to wait for picks in the open session |
| mode | string | no | auto (default): their own Chrome when reachable, else a window |
| wait | number | no | seconds to wait for picks (default 240, at most 600) |
| stop | boolean | no | close the picking session |
| dev_url | string | no | where the person's own site runs in dev (e.g. http://localhost:3000/pricing); found by itself when omitted |
| say | string | no | a short line to show in the picker toolbar, e.g. "✓ Added to Hero.tsx, 99% match" (then it keeps waiting for picks unless wait is 0) |
Check a component you built against the one the person picked: screenshots it in their running app (the local url and a CSS selector for it) and compares it with the original, aligned to the pixel. Returns the difference and, when it is off, a sheet of original | yours | difference (bright =…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pick | string | yes | the pick folder (from site_pick) |
| url | string | yes | where the component renders, e.g. http://localhost:3000/pricing |
| selector | string | yes | a CSS selector for your component on that page |
| hover | boolean | no | compare the hover state instead (needs original-hover.png) |
Clone one part of a website exactly: a button, a card, a nav bar, a hero, a pricing table. Without a selector, a Chrome window opens on the page and the person hovers and clicks the part they want (↑ picks its parent); tell them that first. With a selector, it is taken directly. Snapshots its…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | the page the component is on |
| selector | string | no | a CSS selector for it (skips the picker) |
| name | string | no | a short name for it, e.g. "hero button" |
| wait | number | no | seconds to wait for the click (default 180) |
Score a rebuild against the original site: both pages loaded and scrolled at each width, compared band by band (SSIM, 1 = identical). Returns the scores, the page heights, and for each band under … a sheet of original | clone | difference (bright = different) with its y position. Fix the worst…
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 Site Prompt 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 0.2.1 · scanned 7 Nov 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
Findings6 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestcd65fbbb53e49370dc7ebf8cfc69d9531f5b9ab82923300775be46c77e6ca944
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 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. high 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. | ||
can send data / act on an external service
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 digestcd65fbbb53e49370
Scanned2026-11-07
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 0.2.1. Pin a release below and the command asks for exactly that one.
0.2.1
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 Site Prompt 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.