lo-eyes

Visual accessibility inspector.

Connector by sophiacave · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)

Chalk Labs

Need help deploying lo-eyes?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/sophiacave-lo-eyes

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 4 read · 0 write · 0 delete · 1 not yet classified
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 5

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

eyes_compare
eyes_devices
eyes_scan
eyes_screenshot

Not yet classified 1 · We could not tell from the name and description.

eyes_audit

Tools (5)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

eyes_audit
Run responsive + accessibility audit across viewports. Checks for: overflow, small fonts (<12px), touch targets (<44px), heading hierarchy. Returns a grade (S+ to F) and detailed issues. Args: url: URL path to audit devices: Comma-separated device list (default: all). E.g. "iphone-14,desktop"
eyes_compare
Visual regression: pixel-diff a page against its saved baseline. First call with save_baseline=true to capture a baseline. Later calls capture the page again and report the percentage of changed pixels (anti-alias tolerant). Above threshold, writes a red-highlight diff image showing exactly what changed. Args: url: Full URL or path to compare device: Device preset -- iphone-se, iphone-14, ipad, laptop, desktop save_baseline: Capture/overwrite the baseline instead of comparing threshold: Max percent of changed pixels considered a match (default 0.5)
eyes_devices
List available device presets with their viewport dimensions.
eyes_scan
Auto-chunk a full page into viewport-sized readable screenshots. Captures the entire page as sequential viewport-sized chunks with overlap. Each chunk is readable at full detail. Outputs a manifest for RAG indexing. Args: url: URL path to scan device: Device preset overlap: Pixel overlap between chunks (prevents missing content at fold boundaries)
eyes_screenshot
Take a viewport-sized screenshot of a likeone.ai page. Args: url: URL path (e.g. "/" or "/blog/claude-custom-instructions-guide/") device: Device preset — iphone-se, iphone-14, ipad, laptop, desktop

Signals

Stars: 0
Forks: 0
Open issues: 0
Weekly downloads: 23
Last commit: Jun 10, 2026 (4 months ago)
Last release: Jun 10, 2026 (4 months ago)
Last package publish: Jun 10, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.sophiacave/lo-eyes
Version: 1.1.0
Auth: No auth
Packages: pypi lo-eyes
License: MIT
Repository: github.com/sophiacave/lo-eyes
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

More from sophiacave

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get lo-eyes running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying lo-eyes?

Call Get help

Cite this page

lo-eyes MCP server. Agent Mart. https://agentmart.dev/connectors/sophiacave-lo-eyes (last updated 2026-10-24)