Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Runs on your computer
Macos Vision MCP
Overview
Description from the maker (original English)
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiVery new↓ 128/wk · ★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Other
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- The registry lists no key to fill in.
You need
- npmNode.js installed (for the npx command)
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"macos-vision": {
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}Run this in your terminal
claude mcp add macos-vision -- npx -y macos-vision-mcpOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"macos-vision": {
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"macos-vision": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account woladi, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Otheri
- More stars than 0% of the other 18474 servers in this category
- Published to the registry more recently than 29% of the other 18474 servers in this category
- Basic checks equal to or better than 100% of the other 18474 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Macos Vision MCP safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed –, and the latest version (0.7.0) reached the registry 2 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: Spec Driven Development, Remote Desktop Commander, Brontide agent arena
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Remote Desktop Commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Runs in the cloud✓ desktopcommander.app
Brontide agent arena
THE MECH ARENA BUILT FOR AI AGENTS. HUMANS WELCOME. Pilot mech duels over MCP, free, no sign-in.
Runs in the cloud✓ brontide.live
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
macos-vision-mcp
Your documents and your screen stay on the machine. Only extracted text and structured JSON ever reach the model.
Local, private, offline OCR and UI testing for any MCP client — no API keys, no uploads. Cut document token costs by ~97%, and let an agent see and click your Mac's UI without a single screenshot leaving the machine.
Pre-extracts text and image data locally before your AI ever sees it — cutting token usage by ~97% on real documents and returning structured paragraphs, lines, and bounding boxes so the model can reconstruct the document into Markdown, HTML, DOCX, or any other format. Files never leave your Mac: no cloud API, no API keys, no network requests.
How the ~97% is measured: a 44-page scanned PDF sent as page images costs ~73,500 tokens; the same file run through
analyze_documentreturns ~2,400 tokens of extracted text and structure (raw page-image tokens vs. extracted-text tokens). Your numbers vary with page density and tokenizer — treat 97% as the order of magnitude, not a guarantee.
Contents: Quick Start · What you get · What agents use this for · UI testing · Why it's different · Available Tools · Usage · Example workflows · Configuration · Privacy layer
What you get
- OCR for images and PDFs (JPG, PNG, HEIC, TIFF, multi-page PDF) via Apple Vision Framework.
- ~97% token reduction: a 44-page PDF costs ~2,400 tokens instead of ~73,500.
- Reading-order paragraphs + raw text blocks with bounding boxes — rich structure for the model to reconstruct the document into any output format (Markdown, HTML, DOCX, JSON), not a lossy plain-text dump.
- Face detection, barcode/QR reading, and image classification — all on-device.
- Full document pipeline: OCR + faces + barcodes + rectangles in a single tool call.
- Works with Claude Code, Claude Desktop, and Cursor — any MCP-compatible client.
- No files uploaded to any server — processing stays entirely on your Mac.
- UI testing for agents: screenshot a window locally, find an element by its visible text, get back click coordinates, and assert what's on screen — all without uploading the screenshot.
- 100% offline after
npm install— powered by Apple Vision Framework, same engine as Live Text in Photos.app.
❌ Without / ✅ With
❌ Without macos-vision-mcp:
- Sending a 44-page PDF costs ~73,500 tokens
- Every image, invoice, or contract goes through a cloud API
- Sensitive documents leave your machine on every request
✅ With macos-vision-mcp:
- Local Apple Vision pre-extracts text before Claude ever sees it
- ~2,400 tokens for the same 44-page PDF — 97% fewer
- Files never leave your Mac
What agents use this for
Most work an agent does on a Mac needs no deep understanding of a layout. It needs to see what is on screen, find the thing it is looking for, act on it, and confirm what happened. That loop — list_windows → find_element → click (via any input driver) → assert_text — covers a lot, and every step of it runs on the machine.
- Drive an app that has no API. Native tools, Electron apps, internal software, anything with a GUI and no scripting interface.
find_element("Export")returns the point to click. - Read what is on screen right now. A dialog, an error banner, a notification, a progress state — including a window sitting behind others, without bringing it to the front.
- Confirm an action actually worked.
assert_textis string matching after unicode normalisation, so it answers pass/fail the same way every time instead of asking a model to judge a picture. - Pull data out of software that will not export it. OCR a window, get the text, move on.
- Audit accessibility.
ui_snapshotreports every piece of visible text the accessibility tree does not account for — unlabelled controls and custom-drawn text, with coordinates. - Test a UI for regressions. The case this started as, and still a good one — see the chapter below.
- Work through documents. The original job: invoices, contracts, scans, PDFs.
Why doing it locally is better, not just different
Cheaper. A verdict costs ~240 tokens against ~6,900 for the screenshot it replaces — about 29×. Over a twenty-step task that is ~4,800 tokens instead of ~138,000. It is the difference between an agent that can afford to check its work after every step and one that cannot.
More private, and this is the part that never shows up on a bill. A screenshot is not a neat crop of the button you cared about. It carries whatever else was on screen: another window, a password manager, an open inbox, a customer's record. Sending one to a third party is a disclosure you cannot withdraw, and it repeats on every single step. Here the image is written to a temp file, read by a model on the Neural Engine, and never serialised into the conversation. That invariant is enforced in the code, not promised in this README: no tool returns image bytes.
Faster in practice, and predictable, which matters more. find_element takes 1.17–1.25 s end to end on an M1 Pro — capture 0.31–0.41 s, OCR ~1.04 s, matching under a millisecond. There is no network term at all: no ~750 KB upload before inference can start, no rate limit, no provider under load, no failure when the Wi-Fi drops. The same call costs the same on a plane as it does at a desk.
What this does not do: click. It is eyes, not hands, and therefore never asks for control of
your machine. Pair it with an input driver —
cliclick, amacos-mcp-style automation server,
or anything that accepts screen coordinates — and hand it the
clickPointthatfind_element
returns. The split is deliberate: seeing and acting are different permissions, and this server
only ever asks for the first.
UI testing without sending screenshots anywhere
The usual way to let an agent work with a GUI is to screenshot the screen and upload it to a vision model. That is one network round trip, one image-token bill, and one copy of whatever was on screen — per step. A ten-step flow means ten uploads of your desktop.
This server does the seeing locally. Apple's Vision framework runs on the Neural Engine, so the screenshot stays on disk and only text, geometry, and verdicts reach the model.
What the agent actually receives. Element boxes, roles and labels — measured, not guessed — and the exact point to click. The screenshot itself never leaves the Mac.
find_element(query: "Save", app: "MyApp")→ { found: true, matches: [{ text: "Save", method: "exact", clickPoint: { x: 812, y: 556 }, bbox: {...} }] }
hand clickPoint to any input driver — macos-mcp, cliclick, CGEvent
then verify, again locally:
assert_text(expect: "Saved", app: "MyApp") → { pass: true, ... }
clickPoint is in global screen points with a top-left origin — the same space click drivers use, so it goes straight to a driver with no conversion. This server deliberately does not click: it is eyes, not hands, and therefore never asks for control of your machine.
Is it actually cheaper, safer, and faster?
Measured on an Apple M1 Pro (2021, 16 GB) against a 2992×1734 Retina window capture of a real, text-dense app — median of five runs each.
| Local (this server) | Screenshot → cloud vision API | |
|---|---|---|
| Tokens per step | ~240 (an assert_text verdict) | ~6,900 (image tokens for 2992×1734) |
| Data leaving the Mac | none | ~750 KB PNG of your screen, per step |
| Network | none — works offline, on a plane, behind an air gap | one round trip per step |
| Latency | 1.17–1.25 s end-to-end for find_element | upload + inference + return |
| Cost | $0 | per-image, per-step, forever |
Image tokens are estimated with Anthropic's
width × height / 750rule; other providers
tile differently, so the exact figure moves but the order of magnitude does not. Local token
counts are the actual JSON payloads the tools returned, at ~4 characters per token.
Same question, same answer, ~29× the price. Measured on an M1 Pro against a 2992×1734 window capture.
The three claims behind that table — cheaper, safer, faster — are argued in What agents use this for above. What this section adds is the measurement: the numbers are a median of five runs on an Apple M1 Pro (2021, 16 GB) against a 2992×1734 Retina capture of a real, text-dense window.
We have not benchmarked any specific vision provider, so treat the right-hand column as structure rather than a measured figure. What can be stated is that the local path has no variance from bandwidth, rate limits or provider load, and does not fail when the network does.
Two honest caveats. Targeting a single region instead of a whole window cuts the OCR term sharply, since cost scales with pixels searched. And the first call after install spends ~2 s compiling a small Swift helper; every call after that is warm.
What it is good at — and what it is not
Good at: **native macOS apps, Electron apps with poor accessibility
Only the beginning is shown; read the rest in the repo