Uisight runs on your own machine — the client starts it, so there is no endpoint to ping. 218 installs a week from npm. Last commit 16 Sep 2026.
Your AI sees the screen but can't measure it — measured web UI findings, shared live sessions
We read the source, 3 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
serverProcess = spawn(nodeCommand, args, { cwd, windowsHide: true, shell: true });
import { mkdirSync, writeFileSync, readdirSync, readFileSync, renameSync } from 'node:fs';
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add uisight -- npx -y uisight
{
"mcpServers": {
"uisight": {
"command": "npx",
"args": [
"-y",
"uisight"
]
}
}
}
[mcp_servers.uisight]
command = "npx"
args = ["-y", "uisight"]
{
"mcpServers": {
"uisight": {
"command": "npx",
"args": [
"-y",
"uisight"
]
}
}
}
{
"servers": {
"uisight": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"uisight"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
UISIGHT_URL (Initial target URL for the live sessions (default: http://localhost:3000)), UISIGHT_PORT (Panel server port (default: derived from the project's working directory, so parallel projects get separate panels)), UISIGHT_LANG (Set to 'tr' for Turkish tool names).
Search your saved Captures and Collections, then save useful findings to Scuba.
Your agents share what they learn. Semantik finds it by meaning, with no topic names to agree on.
ASO Scanner — the free Agent Readiness scanner as an MCP server. Measures your ASO Score (Agent.
Agent Readiness MCP — the free Agent Readiness scanner as an MCP server. Measures your ASO Score.
ASO Score MCP — the free ASO Score scanner as an MCP server. Measures your ASO Score (Agent.
The second brain your AI agents share. It builds itself from your work and keeps itself current.
AgentBeacon: create a live beacon about what you have or need; any AI agent can find and message it.
Shared, living memory for you and your people — coves your AI assistant can read and write.
Answers built from our own checks of this server.