Connection check
local install
macos-vision-mcp
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
Tools
13
GitHub stars
—
Installs / wk
1.8k
Licence
—
Transport
stdio
Last checked
never
Tools & capabilities
13 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
analyze_document
from source
assert_text
from source
Assert that text is present on (or absent from) the screen, a window, or a pre-captured image — a local pass/fail verdict computed on this machine. The deterministic check runs her… Assert that text is present on (or absent from) the screen, a window, or a pre-captured image — a local pass/fail verdict computed on this machine. The deterministic check runs here; no screenshot and no OCR dump needs to reach a cloud model for a UI test to pass. USE WHEN: Verifying UI state after an action:
capture_screen
from source
Take a screenshot locally — of the main display, a specific window, an app Take a screenshot locally — of the main display, a specific window, an app
classify_image
from source
detect_barcodes
from source
detect_document
from source
detect_faces
from source
find_element
from source
Find a UI element by its visible text and return WHERE TO CLICK — center coordinates in global screen points, ready to hand to any input driver (macos-mcp Click, cliclick, CGEvent)… Find a UI element by its visible text and return WHERE TO CLICK — center coordinates in global screen points, ready to hand to any input driver (macos-mcp Click, cliclick, CGEvent). Capture, OCR, and matching all run locally; no screenshot is ever sent to the model or the cloud. USE WHEN: An agent needs to click/interact with something it can name (
list_windows
from source
ocr_image
from source
read_screen_text
from source
Capture the screen (or a window/app/region) and OCR it in one step — fully local, the screenshot never leaves this machine. Returns the visible text so you can check UI state witho… Capture the screen (or a window/app/region) and OCR it in one step — fully local, the screenshot never leaves this machine. Returns the visible text so you can check UI state without sending any image to the cloud. USE WHEN:
ui_snapshot
from source
Return the layout of an app Return the layout of an app
vision_capabilities
from source