
lo-eyes
MCP server by github.com/sophiacave/lo-eyes
Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.
About lo-eyes
lo-eyes is an MCP (Model Context Protocol) server published by sophiacave in the official MCP registry. Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.
It ships as a Python package on PyPI (lo-eyes), so any MCP client that can launch a local process can run it.
Development happens in the open at github.com/sophiacave/lo-eyes.
Use lo-eyes with your agent
claude mcp add lo-eyes -- uvx lo-eyes{
"mcpServers": {
"lo-eyes": {
"command": "uvx",
"args": [
"lo-eyes"
]
}
}
}lo-eyesFrequently asked questions
- What is lo-eyes?
- lo-eyes is an MCP (Model Context Protocol) server by sophiacave. Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.
- How do I connect lo-eyes to Claude, Cursor, or another MCP client?
- Install lo-eyes from its pypi package (lo-eyes) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
- Is lo-eyes open source?
- Yes — the source code is public at github.com/sophiacave/lo-eyes.
- Can AI agents pay to use lo-eyes?
- Not yet through Loomal — lo-eyes is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.
More MCP servers

human-dispatch-mcp
0
MCP server that dispatches physical-world tasks to humans through a unified API

VMware Storage
0
VMware vSphere storage management with 11 MCP tools: datastores, iSCSI, vSAN.

VMware NSX Security
0
VMware NSX security: DFW policies, security groups, tags, Traceflow, IDPS — 21 MCP tools.

VMware AVI
0
VMware AVI (NSX ALB) load balancer plus AKO Kubernetes ops — 29 MCP tools.

VMware Aria Operations
0
VMware Aria Operations: metrics, alerts, capacity, anomaly detection — 18 MCP tools.

MeatSpace
0
Human-in-the-loop for AI agents. Submit choices, get a human decision.
Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain lo-eyes? Claim this listing free by verifying GitHub ownership, or contact us.