Pir Mcp

io.github.Solteris-Dev由 GitHub 账号 Solteris-Dev 发布v0.1.0更新于 Oct 24, 2026

Motion sensor for AI agents: tells when a screen region changes or goes still. Scores, never pixels.

已验证STDIO仅桌面浏览器自动化开发者工具

概览

AI 生成的概览

让助手监视指定的屏幕区域,以数值分数而非图像报告区域是否发生变化或已静止。

可以做什么
它定义具名的屏幕矩形或窗口并按需采样,在粗粒度平均颜色网格上返回两个变化分数:rmse 表示整个区域是否移动,peak 表示变化最大的单个格子。工具包括由人绘制区域的 pir_pick_region 和 pir_pick_mask、用于脚本化几何的 pir_define_region 和 pir_define_window、一次性检查的 pir_sample,以及阻塞等待区域变化或静止的 pir_wait_for_change 和 pir_wait_for_stillness。它从不返回像素、图像文件或任何可还原为图片的内容。
适用场景
适合驱动桌面的助手在不看屏幕的情况下判断某处是否发生变化或停止变化,例如等待构建输出更新,或检测状态栏是否卡死。适用于长时间监视,此时截图既无必要也过于暴露。
运行要求
以 npm 包(npx pir-mcp)在本地运行,需要 Node 20+。需要能向标准输出写入二进制 PPM 的截图工具,通过 PIR_CAPTURE_CMD 配置(wlroots 下默认 grim)。可选的选择器与窗口命令通过 PIR_SELECT_CMD、PIR_PICK_WINDOW_CMD 和 PIR_WINDOW_GEOMETRY_CMD 设置;留空会禁用相应工具。仅限桌面。
安装前请注意
它通过你配置的命令截取屏幕,并以你的权限运行,因此拥有该命令本身的屏幕访问权限。它会透露某个矩形在某个时间以某个幅度发生了变化;若区域覆盖聊天窗口,这属于在线状态信息,请据此选择区域。阻塞调用受 PIR_MAX_WAIT_MS 限制,应低于宿主工具超时。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Pir Mcp,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

pir-mcp

A motion sensor for AI agents.

"Gives your LLM agents enough info to be a helpful "watcher" without being a privacy nightmare like Windows Recall" -Solteris-Dev

[pir-mcp MCP server – quality and maintenance score on Glama]

A PIR sensor tells you that something moved, never what. This is the same idea for a screen: an MCP server that watches named rectangles and answers "did this change?" and "has this gone still?" with a number, a size and a timestamp. No tool in it returns pixels, image files, or anything that could be turned back into a picture.

It exists because an agent driving a desktop keeps needing the same two things: wake me when the build output moves and tell me if this status bar has stopped ticking. Both are motion questions. Neither needs a screenshot.

What it does

  • pir_pick_region ask the person at the screen to draw the rectangle, the way a regional screenshot works (slurp, slop). The human chooses what is sensed; the agent gets the geometry. Use this whenever someone is there.
  • pir_pick_mask the same gesture for a patch inside a region to ignore (a clock, a spinner, a caret).
  • pir_define_region the scriptable path: name a rectangle by global layout coordinates, with optional masks.
  • pir_pick_window / pir_define_window watch a window instead of a fixed rectangle. Its geometry is looked up again before every capture, so the region follows the window when it moves; a resize counts as maximal change. The pick offers your visible windows as boxes to click.
  • pir_sample capture once, score against the previous sample of that region. Cheap; also the way to check the capture command works.
  • pir_wait_for_change block until the region departs from how it looked when the call began, or time out. A doorbell.
  • pir_wait_for_stillness block until nothing has changed for still_for_ms, or time out. A short window means "the animation settled, safe to act". A long window on something that should keep changing means it is frozen, and still=true is the alarm.
  • pir_list_regions, pir_remove_region housekeeping.

Every comparison reports two numbers over a coarse grid of averaged colour cells (at most 64 across, each at least 4 px), both 0 for identical and 1 for black against white:

  • rmse over the whole grid: did the region as a whole move? A cursor edge or an antialiased caret scores about 0.02; a dialog opening 0.1 or more. This is the default metric, threshold 0.05.
  • peak the single most-changed cell: did anything in it move? A clock digit flipping inside a 1920-wide status bar scores rmse 0.018 (invisible to the default) but peak 0.145. Use metric=peak for a small thing that should tick inside a larger region.

Averaging is what makes this a sensor rather than a camera: 64 cells cannot be read.

What it deliberately does not do

  • It never returns image data. There is no snapshot tool and none is planned. If an agent needs to see, use the screenshot tool your environment already has, so that choice stays explicit and yours.
  • It never writes frames to disk. A capture lives in memory for the milliseconds it takes to reduce it to a grid, and only the grid of the last sample is kept per region.
  • It does not capture on its own. Every sample is a tool call the agent made, visible in the transcript, and pir_pick_region carries a purpose line the agent has to write down before you draw.

What it does reveal, so you can decide whether that is acceptable: that a given rectangle changed, at a given time, by a given magnitude. On a region covering a chat window that is presence information. Choose regions accordingly; the server has no opinion.

The capture itself is delegated to a command you configure, run with your privileges. The default is grim, so nothing here has screen access that you did not already give to grim.

Install

It is on npm as pir-mcp and in the official MCP Registry as io.github.Solteris-Dev/pir-mcp, so most clients can run it with npx -y pir-mcp and no clone:

sh
claude mcp add -s user pir -- npx -y pir-mcp

From source:

sh
git clone https://github.com/Solteris-Dev/pir-mcpcd pir-mcp && npm install && npm run build

Requires Node 20+ and a screenshot tool that can write binary PPM to stdout.

Capture command

PIR_CAPTURE_CMD is a template; {x} {y} {w} {h} are substituted and the result runs under sh -c. It must print a binary PPM (P6) to stdout.

environmentcommand
wlroots / Hyprland / Sway (default)grim -g "{x},{y} {w}x{h}" -t ppm -
X11 with maimmaim -g {w}x{h}+{x}+{y} -f png | magick png:- ppm:-
X11 with ImageMagickimport -window root -crop {w}x{h}+{x}+{y} +repage ppm:-
macOSscreencapture -x -R{x},{y},{w},{h} -t png /dev/stdout | magick png:- ppm:-

Coordinates are whatever the capture tool uses. On a wlroots layout that is the global layout, so an output placed left of the primary has negative x.

Selector command

PIR_SELECT_CMD runs when an agent calls pir_pick_region or pir_pick_mask and must print x,y wxh. Set it to an empty string to remove those tools entirely.

environmentcommand
wlroots / Hyprland / Sway (default)slurp -f "%x,%y %wx%h"
X11slop -f "%x,%y %wx%h"
macOSsee contrib/macos (untested)

Window commands

PIR_WINDOW_GEOMETRY_CMD gets {id} substituted and must print x,y wxh for that window; PIR_PICK_WINDOW_CMD must print the id of the window the person chose. Both default to Hyprland (via jq and slurp -r). Set either to an empty string to remove the corresponding tools. Window ids are limited to [A-Za-z0-9_.:-] before they reach a shell.

environmentgeometrypick
Hyprland (default)hyprctl -j clients | jq -r --arg id "{id}" '.[] | select(.address==$id) | "\(.at[0]),\(.at[1]) \(.size[0])x\(.size[1])"'visible windows as slurp boxes, prints the address
Swayswaymsg -t get_tree | jq -r '.. | select(.id? == {id}) | "\(.rect.x),\(.rect.y) \(.rect.width)x\(.rect.height)"'swaymsg -t get_tree | jq -r '.. | select(.visible? == true) | "\(.rect.x),\(.rect.y) \(.rect.width)x\(.rect.height) \(.id)"' | slurp -r -f '%l'
X11xdotool getwindowgeometry --shell {id} | awk -F= '/^X/{x=$2}/^Y/{y=$2}/^WIDTH/{w=$2}/^HEIGHT/{h=$2}END{print x","y" "w"x"h}'xdotool selectwindow

Only the Hyprland pair has been run; the others are written from the tools' documentation.

Claude Code

sh
claude mcp add -s user pir -- npx -y pir-mcp# or, from a source checkout:claude mcp add -s user pir -- node /path/to/pir-mcp/dist/stdio.js

Blocking calls default to 55 s and are capped by PIR_MAX_WAIT_MS (540 s). Keep the cap under your host's MCP tool timeout; an agent that needs to watch for longer just calls again.

Other settings

variabledefaultmeaning
PIR_REGIONSunsetJSON file of regions to define at startup
PIR_THRESHOLD0.05default change threshold
PIR_INTERVAL_MS500default sampling period
PIR_DEFAULT_WAIT_MS55000default timeout for blocking calls
PIR_MAX_WAIT_MS540000cap for blocking calls
PIR_CAPTURE_TIMEOUT_MS10000how long one capture may take
PIR_SELECT_TIMEOUT_MS60000how long the person has to draw a selection
PIR_MAX_CELLS64grid resolution on the long side; smaller is coarser and more private

A regions file looks like:

json
[  { "name": "bar", "x": 0, "y": 0, "w": 1920, "h": 26,    "masks": [{ "x": 1690, "y": 0, "w": 110, "h": 26 }] }]

Example

The case that produced this: a status bar that occasionally froze for hours while its process looked healthy. The clock in it should change every minute, so a bar that is still for three minutes is a frozen bar.

pir_pick_region         name=bar purpose="watch the status bar for a freeze"pir_wait_for_stillness  name=bar still_for_ms=180000 metric=peak timeout_ms=540000

still=true comes back only if the bar stopped; otherwise the call returns still=false at the timeout and the agent calls again. Nothing on the screen was ever seen, and the person drew the rectangle themselves.

Contributing starting points

contrib/macos/ holds an AppKit rectangle selector and capture recipe, written blind and untested. If you run it on a real Mac, fix what breaks and send it back.

Tests

sh
npm test

License

MIT.

来源:README.md,提交 833ded4

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.0最新Sep 17, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分