Pir MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 148 installs a week from npm. Last commit 21 Sep 2026.
Motion sensor for AI agents: tells when a screen region changes or goes still. Scores, never pixels.
Today is the operative word: we check Pir MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 pir-mcp -- npx -y pir-mcp
{
"mcpServers": {
"pir-mcp": {
"args": [
"-y",
"pir-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.pir-mcp]
command = "npx"
args = ["-y", "pir-mcp"]
{
"mcpServers": {
"pir-mcp": {
"args": [
"-y",
"pir-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"pir-mcp": {
"args": [
"-y",
"pir-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
PIR_CAPTURE_CMD (Screenshot command template writing binary PPM to stdout; {x} {y} {w} {h} substituted. Default: grim (wlroots).), PIR_SELECT_CMD (Interactive rectangle selector printing 'x,y wxh'. Default: slurp. Empty disables the pick tools.), PIR_WINDOW_GEOMETRY_CMD (Prints 'x,y wxh' for window {id}. Default: Hyprland via jq. Empty disables window regions.), PIR_PICK_WINDOW_CMD (Interactive window pick printing the window id. Default: Hyprland + slurp.), PIR_MAX_WAIT_MS (Cap for blocking calls, ms (default 540000); keep under the host's MCP tool timeout.).
The author declared them in the registry entry; get the values from the project itself.
Resolve, discover & pay pay: aliases for AI agents; returns a signed OFAC-screen attestation.
MCP server for Site Spy — lets AI agents monitor websites for changes
A secret store for AI agents: the agent never sees the plaintext.
Impact preview for AI agents - see what changes before any action executes.
Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.
Skills and Scars for AI agents - your agent records its failures and never repeats them.
Look up on-chain Attribution reputation scores for wallets and AI agents on Base.
JSDoc, README, changelog generation for AI agents
Answers built from our own checks of this server.