macos-vision-mcp

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_document returns ~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_text is 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_snapshot reports 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, a macos-mcp-style automation server, or anything that accepts screen coordinates — and hand it the clickPoint that find_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.

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 / 750 rule; 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.

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, canvas/WebGL UIs, games, and design mockups — anything where there is no DOM to query. Also good when you want a deterministic assertion rather than a model's opinion: assert_text is string matching after unicode normalisation, so it returns the same answer every time.

Not the right tool for a plain web page: Playwright or the DOM will be faster and more precise there. And OCR only sees what is rendered, so it cannot read a control's enabled state or its accessibility role.

Text matching is normalised before comparison — NFC, collapsed whitespace, unicode dashes and quotes folded — then tried exact → substring → fuzzy (Levenshtein). When a match is rejected it is still reported under nearMisses, so "the label is there but OCR read Zapisr for Zapisz" is distinguishable from "the label is genuinely absent".

Substring hits are graded rather than treated alike: a query that stands on word boundaries, opens the label, and covers more of it scores higher. That ordering matters when the answer is a button — for the query Save, Save Changes must outrank Don't Save. Each match reports wholeWord, and assert_text decides its verdict only on matches where it is true: Save inside Unsaved changes is a coincidence of spelling, and it neither proves a Save button is on screen nor proves it is gone. Such hits are still listed, under incidental.

Requirements

• Screen Recording permission for the app hosting the MCP server (Terminal, Claude Desktop, Cursor): System Settings → Privacy & Security → Screen Recording, then restart that app. No compiler or Xcode tooling is needed — the native helper arrives prebuilt.

  The grant is per host process, not per package: the same server can be fully working under one client and blind under another on the same Mac. Without it, capture fails outright and macOS additionally withholds every window title, so list_windows reports title: "" for everything — that case is flagged as titlesAvailable: false rather than left to look like a screen full of untitled windows. Run vision_capabilities first: ready and blockers say what works right now.

• An unlocked Mac. On a locked machine window and region capture fail outright and a full-screen capture returns only the lock screen; vision_capabilities reports screenLocked so an agent can check before it starts rather than guessing at a failure afterwards.

Why it's different

Most OCR options for LLMs either ship your documents to a cloud vision API or make you stand up and tune your own engine. This runs on Apple's on-device Vision framework — the same engine behind Live Text in Photos.app — so extraction is free, private, and instant.

	macos-vision-mcp	Cloud vision OCR (GPT-4o, Google Vision, Mistral OCR)	Tesseract-based MCP
Cost	$0 — no per-page or per-token fees	Per-call / per-page billing	$0, but self-hosted
Offline	Yes, after install	No — every page hits the network	Yes
Privacy	Files never leave your Mac	Documents uploaded to a third party	Local
Setup	One command, no keys	API key + billing account	Install + language data + tuning
Quality	Apple Vision (strong on clean scans, receipts, screenshots)	Generally high	Varies; weaker on poor scans
UI testing	Built in — capture, locate, assert, no uploads	Possible, but every step uploads your screen	OCR only; no capture or targeting

The trade-off is honest: it's macOS-only, and on heavily skewed or low-contrast scans a cloud model may still read more. For the common case — invoices, contracts, receipts, screenshots, clean PDFs — you get cloud-grade extraction with zero cost, zero setup, and nothing leaving your machine.

Privacy layer

macos-vision-mcp acts as a local pre-processing layer between your documents and the cloud. Useful for:

• Legal documents, contracts, NDAs
• Financial reports, invoices, internal spreadsheets
• Medical records or any GDPR-sensitive content
• Any situation where you want to extract structured data locally before deciding what (if anything) to send upstream

Instead of sending the raw document to your AI, you extract the text and structure locally first. The model then works only with the extracted text — never the original file.

The same applies to your screen. A screenshot taken for one small check still carries everything else that happened to be visible — other windows, a password manager, a customer record, an open inbox. The UI-testing tools keep that image on disk and return only paths, geometry, and text, so a UI assertion does not become an unplanned disclosure. No tool in this server returns image bytes to the model.

Quick Start

Add to your MCP client (example for Claude Code):

claude mcp add macos-vision-mcp -- npx -y macos-vision-mcp

Using Claude Desktop or Cursor? Jump to Configuration ↓

Restart your client. npx fetches the package on first run, caches it, and the tools appear automatically — no separate install step. This is the convention used by most MCP servers and recommended by Anthropic, Cursor, and other clients.

Note: On first run, the package downloads prebuilt Swift helper binaries (vision-helper, pdf-helper, ui-helper, ax-helper) from its GitHub Releases (~276 KB compressed, ~1–2s). Subsequent invocations hit the npx cache and start instantly. Xcode Command Line Tools are only required as a fallback when the download can't reach the network — set MACOS_VISION_SKIP_DOWNLOAD=1 to force local compilation with swiftc.

Prefer instant cold-starts (no npx cache lookup)? Install globally with npm install -g macos-vision-mcp and use the alternative config shown at the bottom of Configuration.

Available Tools

Tool	What it does	Example prompt
ocr_image	Extract text from an image or PDF (JPG, PNG, HEIC, TIFF, PDF). Returns plain text, or per-page paragraphs + text blocks with lineId / paragraphId and bounding boxes. Accepts start_page / max_pages for partial PDF OCR.	"Read the text from ~/Desktop/screenshot.png"
detect_faces	Detect human faces and return their count and positions.	"How many people are in this photo?"
detect_barcodes	Read QR codes, EAN, UPC, Code128, PDF417, Aztec, and other 1D/2D codes.	"What does the QR code in /tmp/qr.jpg say?"
detect_document	Detect the four corner points of a document in a photo (paper, receipt, ID). Useful as a crop / deskew hint before OCR.	"Find the document corners in ~/Desktop/receipt.jpg"
classify_image	Classify image content into 1000+ categories with confidence scores.	"What is in this image?"
analyze_document	Returns structured JSON with reading-order paragraphs, raw text blocks (bbox / confidence), faces, barcodes, and rectangles — ready for the model to reconstruct into Markdown, HTML, or anything else. Also accepts start_page / max_pages for long PDFs.	"Reconstruct ~/Desktop/scan.pdf as clean Markdown"

UI-testing tools (local, no screenshots sent to the cloud)

These tools let an agent see and verify your Mac's UI without ever sending a screenshot to a cloud model. Screenshots are captured locally, OCR runs on-device, and only paths, geometry, and extracted text are returned. find_element gives click coordinates in screen points, ready to hand to any input driver (this server deliberately does not click — eyes, not hands).

Tool	What it does	Example prompt
capture_screen	Screenshot the main display, a window (even occluded), an app's frontmost window, or a region. Returns the file path + screen-point frame — never the image bytes.	"Capture the Safari window"
list_windows	List on-screen windows with global screen-point bounds, front-to-back.	"What windows are open?"
read_screen_text	Capture + OCR in one step — read what an app shows right now, fully offline.	"What does the TestFlight window say?"
find_element	Find a UI element by visible text; returns clickPoint {x,y} in global screen points (exact → substring → fuzzy matching with near-miss reporting).	"Where is the Save button in MyApp?"
assert_text	Local pass/fail assertion that text is present on / absent from the screen — the verdict is computed on your Mac, not by a cloud model.	"Verify the dialog says 'Saved' after clicking Save"
vision_capabilities	Report macOS version, Screen Recording / Accessibility permission state, and displays.	"Can this machine run UI tests?"
ui_snapshot	Return the whole layout as JSON: every element's exact box, role, label and state from the accessibility tree, optionally with colours and fonts — plus visible text the tree does not account for.	"Review this dialog's layout" · "What is unlabelled?"