# AI Process Manager (AIPM) (npm · aipm-mcp-server)

Structured Windows state for AI agents: processes, windows, UI trees. No screenshots.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `aipm-mcp-server`: 68/100 (this document), [markdown](https://verifymcp.io/servers/agorapassadoagora-debug-aipm/aipm-mcp-server.md), [page](https://verifymcp.io/servers/agorapassadoagora-debug-aipm/aipm-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `aipm-mcp-server`
- Version: `0.5.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2513 tokens (~125/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add agorapassadoagora-debug-aipm -- npx -y aipm-mcp-server
```

### Codex

```bash
codex mcp add agorapassadoagora-debug-aipm -- npx -y aipm-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agorapassadoagora-debug-aipm": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "aipm-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add agorapassadoagora-debug-aipm --command npx --arg -y --arg aipm-mcp-server
```

### Hermes

```yaml
mcp_servers:
  agorapassadoagora-debug-aipm:
    command: "npx"
    args: ["-y", "aipm-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "agorapassadoagora-debug-aipm": {
      "command": "npx",
      "args": [
        "-y",
        "aipm-mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-01 (score 53, −9)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 62)

First indexed and scored.

## MCP tools (20)

### `health_check` (~37 tokens)

Ping the AI Process Manager backend. Returns version, API URL, and whether the local service is reachable. Call this first in a new session.

### `check_process` (~149 tokens)

Check if a process is running on the user's Windows machine — no screenshot. Filter by executable name fragment (e.g. "python", "ffmpeg") and/or window title (e.g. "RENDER VIDEO 02"). Returns PID, CPU%, RAM, title, command line, start time. Command lines are truncated to 120 chars unless full_command_line=true. Results are capped at 10 matches, windowed processes first.

Input parameters:

- `full_command_line` (boolean): true for full command line (default: truncated to 120 chars)
- `name_contains` (string): Executable name fragment (case-insensitive)
- `title_contains` (string): Window title fragment (case-insensitive)

### `list_processes` (~79 tokens)

List running processes sorted by CPU. Use "top" to limit (default 25, max 200). Prefer check_process when searching for one process. Command lines truncated unless full_command_line=true.

Input parameters:

- `full_command_line` (boolean): true for full command lines
- `top` (number): How many processes to return (default 25)

### `list_windows` (~41 tokens)

List open desktop windows: title, process, minimized/maximized state, position, Z-order, and which has focus. Replaces screenshots for "what is open".

### `get_system_status` (~37 tokens)

Machine snapshot: CPU%, RAM used/total, GPU name and usage, disk free space per drive, network, uptime, active displays.

### `get_taskbar` (~26 tokens)

Human view of the taskbar: pinned apps and running apps grouped with window titles.

### `read_window` (~113 tokens)

Read TEXT from inside a window via UI Automation — no screenshot. Works with consoles (cmd, PowerShell, Windows Terminal), editors, and most native apps. Typical use: read render progress from a console ("frame 4812/5000"). Identify the window by title_contains or hwnd from list_windows.

Input parameters:

- `hwnd` (number): Exact window handle from list_windows
- `max_chars` (number): Max characters (default 20000)
- `title_contains` (string): Window title fragment (case-insensitive)

### `get_ui_tree` (~350 tokens)

UI Automation tree of a window (roles, names, states) — the accessibility snapshot of a native Windows app. depth: default 4, max 30. max_nodes: default 200, max 1000 — max_nodes is the cost brake, NOT depth. Win32 apps expose content within 4-6 levels. Chromium/Electron apps (VS Code, Slack, Discord, Claude Desktop, Teams) bury real content under ~10 levels of Pane/Group wrappers: at low depth you get only empty Panes and conclude, wrongly, that the window is empty. Measured on Claude Desktop: depth=8 -> 15 useless nodes; depth=17 -> 115 nodes, 87 of them named (~8 KB) — the tree saturates at 17. So for Chromium/Electron ask for depth=15-20 and cap cost with max_nodes. The response reports depth, max_nodes, nodes, depth_reached and truncated; when truncated=true the tree was cut (read next_action) and you should repeat with a higher depth and/or max_nodes before concluding anything about the window. For finding a clickable target prefer ui_find (already filtered to interactive elements).

Input parameters:

- `depth` (number): Max tree depth (default 4, max 30). 4-6 for native Win32; 15-20 for Chromium/Electron apps, whose content sits under ~10 wrapper levels.
- `hwnd` (number): Exact window handle
- `max_nodes` (number): Max nodes returned (default 200, max 1000). This is the token-cost brake — raise depth freely and cap cost here.
- `title_contains` (string): Window title fragment

### `wait_for` (~175 tokens)

Long-poll until a condition is met (or timeout). Replaces polling loops. Conditions: process_ended, process_started, file_stable (render/download done), file_exists, window_title_contains. Max 50s per call; if satisfied=false, call again to keep waiting.

Input parameters:

- `file_exists` (string): File path that must appear
- `file_stable` (string): File path that must stop growing
- `process_ended` (string): Process name fragment that must exit
- `process_started` (string): Process name fragment that must start
- `stable_for` (number): For file_stable: seconds unchanged (default 10)
- `timeout` (number): Max wait seconds (default 50, max 50)
- `window_title_contains` (string): Window title fragment that must appear

### `get_recent_events` (~91 tokens)

Last 24h of PC events: process_started, process_ended (with duration), window_focused, file_changed. Useful for "what happened while I was away" (e.g. when did the render finish?).

Input parameters:

- `limit` (number): Max events (default 50, max 1000)
- `type` (string): Filter by type (process_ended, file_changed, ...)

### `check_file` (~56 tokens)

File or folder status: exists, size, last modified, locked?, locking process. Ideal for checking if a render/export finished without opening Explorer.

Input parameters:

- `path` (string, required): Absolute path, e.g. D:/videos/output.mp4

### `get_app_knowledge` (~129 tokens)

Query what AIPM learned locally about an app: successful (role, name) -> action recipes, plus common_failures (targets that keep failing — do not retry them). Call BEFORE acting in an app. Even with known=false you may get ui_shape: the shape of the app's UI tree (counts, roles, depth) learned passively from earlier reads — useful cold-start map. Pass the process name as shown in task manager (e.g. "notepad.exe", "chrome.exe").

Input parameters:

- `name` (string, required): App/process name (e.g. notepad.exe)

### `get_economy_stats` (~88 tokens)

Local economy metrics: tokens and time saved by structured state vs screenshots, queries served, task/action success rates, top apps, 24h/7d trends. Two independent views of savings — economy_measured_by_api (measured here) and economy_reported_by_agents (self-reported): never add them together. The store block states which local database the totals came from.

### `get_audit_log` (~74 tokens)

Recent API audit log: which agents called which endpoints and when. Works even when the API is paused. For compliance and debugging agent behavior. Secrets and typed text (api_key=, value=) are masked before being recorded.

Input parameters:

- `limit` (number): Max entries (default 50, max 1000)

### `ui_find` (~157 tokens)

List interactive UI elements in a window (buttons, fields, menus first; grid cells last). Each item has a stable global element_index plus can_invoke/can_set_value flags. Paginated (total/offset/limit/has_more). Read-only — no action tier required. Pass element_index to ui_invoke/ui_set_value.

Input parameters:

- `hwnd` (number): Exact window handle
- `limit` (number): Page size (default 30, max 200)
- `name_contains` (string): Filter elements by name
- `offset` (number): Pagination offset (default 0)
- `role` (string): Filter by role (Button, Edit, MenuItem, ...)
- `title_contains` (string): Window title fragment

### `ui_invoke` (~114 tokens)

Semantically CLICK a UI element via UI Automation (button, menu item, checkbox). Target by name_contains or element_index from ui_find. REQUIRES user-enabled action tier + app allowlist; otherwise returns action_denied. Confirm with the user before acting.

Input parameters:

- `element_index` (number): Stable index from ui_find
- `hwnd` (number): Exact window handle
- `name_contains` (string): Element name to click (e.g. "Save")
- `title_contains` (string): Window title fragment

### `ui_set_value` (~116 tokens)

Set text in an editable field via UI Automation (no key simulation). REQUIRES action tier + allowlist. Check can_set_value in ui_find; modern apps (e.g. Win11 Notepad) may not expose fields. Confirm with the user first.

Input parameters:

- `element_index` (number): Stable index from ui_find
- `hwnd` (number): Exact window handle
- `name_contains` (string): Field name
- `title_contains` (string): Window title fragment
- `value` (string, required): Text to set

### `focus_window` (~46 tokens)

Bring a window to the foreground. REQUIRES action tier + app allowlist.

Input parameters:

- `hwnd` (number): Exact window handle
- `title_contains` (string): Window title fragment

### `report_task_outcome` (~143 tokens)

Report task outcome to local telemetry (metadata only — never screen content). Call at END of a computer-use task. Feeds get_app_knowledge and get_economy_stats.

Input parameters:

- `app` (string, required): Primary app (e.g. chrome.exe)
- `duration_s` (number): Duration in seconds
- `notes` (string): Short notes (metadata)
- `screenshots_avoided` (number): Screenshots avoided via structured state
- `steps` (number): Number of steps/actions
- `success` (boolean): Task succeeded?
- `task` (string): Short task description (metadata)
- `tokens_estimated` (number): Estimated tokens consumed

### `report_action_outcome` (~233 tokens)

Report one UI action outcome (invoke/set_value/focus). Feeds per-app recipes in get_app_knowledge. Metadata only — never screen content or typed text. Report FAILURES too (ok=false plus reason): they become common_failures and stop the next agent from repeating the same dead end.

Input parameters:

- `action` (string, required): Action performed (invoke, set_value, focus)
- `app` (string, required): App where action occurred
- `element_name` (string): Element name (e.g. "Save")
- `element_role` (string): Element role (Button, Edit, ...)
- `ms` (number): Action duration in ms
- `ok` (boolean): Action succeeded?
- `reason` (string): Only when ok=false. Closed vocabulary: elemento_nao_encontrado, elemento_nao_suporta_invoke, elemento_nao_suporta_set_value, campo_somente_leitura, janela_nao_encontrada, ui_timeout, acao_bloqueada,…

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/agorapassadoagora-debug-aipm/aipm-mcp-server#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 68
- 2026-08-01: 53
- 2026-07-31: 62

## Links

- npm package: https://www.npmjs.com/package/aipm-mcp-server
- Socket report: https://socket.dev/npm/package/aipm-mcp-server
- Repository: https://github.com/aipm-engine/AIPM
- Changelog RSS feed: https://verifymcp.io/servers/agorapassadoagora-debug-aipm/aipm-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/agorapassadoagora-debug-aipm/aipm-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/agorapassadoagora-debug-aipm/aipm-mcp-server