Spacing & grid QA for AI-generated UIs, in the agent loop. MCP server that audits computed geometry and returns fix hints.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add gridproof -- npx -y gridproof~/.codex/config.toml
[mcp_servers.gridproof]
command = "npx"
args = ["-y", "gridproof"]
# codex mcp add gridproof -- npx -y gridproof~/.cursor/mcp.json
{
"mcpServers": {
"gridproof": {
"command": "npx",
"args": [
"-y",
"gridproof"
]
}
}
}.vscode/mcp.json
{
"servers": {
"gridproof": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gridproof"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"gridproof": {
"command": "npx",
"args": [
"-y",
"gridproof"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"gridproof": {
"command": "npx",
"args": [
"-y",
"gridproof"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"gridproof": {
"command": "npx",
"args": [
"-y",
"gridproof"
]
}
}
}