io.github.xyun1996/ocularweb-automation

ocular

Verified · 18 days ago

Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.

Install

claude mcp add ocular -- npx -y [email protected]

Requires: OCULAR_BASE_URL, OCULAR_API_KEY, OCULAR_MODEL

Our take

This server provides vision-oriented tools for coding agents, including screenshots, OCR, UI diffs, error capture, and structured extraction from tables and charts. It is for agent workflows that need to inspect graphical interfaces rather than only text or APIs. The feature set is broader than many single-purpose MCP servers, but with no public usage signal it still looks early and worth testing carefully for reliability and performance.

reviewed by hand · 2026-08-13

Something wrong or dead here? Report it

Verification record

last verified
18 days ago
github stars
0
last commit
2 mo ago
archived
no
license
MIT
downloads / wk
19
latest version
0.1.0
in registry since
2026-08-12

github.com/xyun1996/ocular

browser-useweb-automation

browser-use

Verified · 26 days ago

Control a real Chrome browser to complete any task: fill forms, extract data, book flights.

hand-reviewed112k starschecked 26 days ago

Scrapling MCP Server

Verified · 19 days ago

Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.

hand-reviewed79k starschecked 19 days ago

playwright-mcpweb-automation

playwright-mcp

Verified · 21 days ago

Playwright Tools for MCP

hand-reviewed37k stars5.9m dl/wkchecked 21 days ago

invisible-playwright-mcpweb-automation

invisible_playwright_mcp

Verified · 3 days ago

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

hand-reviewed32k starschecked 3 days ago

AIHawk

Verified · 14 days ago

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

hand-reviewed30k starschecked 14 days ago