github analyzed · update queued f4f897f unconfirmed MCP

AppControlLabs/appcontrol-mcp-go

github

AppControl MCP is a local server connecting AI agents and IDEs like Claude, Cursor, and Windsurf to system history provided by the AppControl desktop app. Ask which apps used CPU, GPU, RAM, or disk, and what caused slowdowns, heat spikes, or webcam, mic, and location access. Built for deep historical monitoring and useful real-world PC insights.

maintainer
AppControlLabs
license
MIT
first seen
2026-06-01
last seen
2026-06-04
releases · 30d
0
short id

Drift inferred · capture-to-capture

No drift recorded — single capability capture; advisories appear once its surface changes.

capabilities 9 tools
transport counts 9 tools · 0 res · 0 prompts permission surface via code analysis

tools

  • get_binary

    Get detailed info for one or more binaries by ID (batch with comma-separated IDs) — path, hash, signature, publisher, first-seen time, and running status.

  • get_hardware

    Get CPU, GPU, and temperature sensor info for the monitored system.

  • get_monitoring

    Get time-series resource metrics — system-wide (CPU, memory, disk, GPU, temps) or per-binary with top-N/min-value filtering to find heavy resource consumers.

  • get_stats

    Get service stats, current timestamp, and uptime/idle intervals showing when the PC was on, off, or idle.

  • list_binaries

    List tracked binaries with filters — unsigned-only, currently-running, first-seen-after date, path substring, or publisher ID.

  • list_processes

    List currently running processes with binary ID, name, path, PID, and start time. Filterable by fields.

  • list_publishers

    List code-signing publishers (certificate identities) — name, country, and linked binary/rule counts.

  • list_rules

    List quarantine rules — blocked binaries and publishers with rule type and creation time.

  • query_history

    Query security event history — binary first-seen events, quarantine blocks, alerts, and process starts. Filterable by event type, time range, and binary ID.

code evidence vv1.0.0 · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

No code evidence — the analyzed source reached for no tracked permissions, tools, or hooks.