Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ast action1

    1

    Control Action1 RMM endpoints to audit inventory, processes, and software, or deploy scripts and packages securely.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ast action1

    ast action1

    Example session with this skill installed

    Check the online status of host 'WS-PROD-01' and list all running processes to see if 'chrome.exe' is active.

    • Read your context and instructions
    • Compiled the ast action1

    I have checked the status and process list for the requested host via the Action1 API.

    Endpoint Audit: WS-PROD-01

    DetailValueSource
    StatusOnlineaction1 devices --id WS-PROD-01
    Last Seen2024-05-20 14:02:11 UTCaction1 devices --id WS-PROD-01
    Active Processes142action1 processes --id WS-PROD-01
    Chrome Searchchrome.exe (PID 4402, 8812, 9010)action1 processes --id WS-PROD-01 --filter chrome

    Gaps

    The search was limited to active processes at the time of the query. Historical process data was not inspected. No errors were reported by the Action1 API.

    Next steps

    • If you need to terminate these processes, I can prepare an action1 run script command. Needs your approval.
    • I can fetch the installed software version for Chrome to check for vulnerabilities.
    • To stop the process, use: action1 run --id WS-PROD-01 --script "Stop-Process -Name chrome -Force".

    Needs your approval.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Managing remote endpoints at scale often involves constant context switching between the Action1 dashboard and your terminal. This skill provides a direct interface to Action1 RMM, allowing you to audit device inventory, inspect live processes, and manage software deployments without leaving your development environment. It bridges the gap between endpoint visibility and automated remediation while maintaining a strict safety model for production environments.

    What it does

    • Device Inventory Retrieves hardware details, online status, and network adapter configurations for managed workstations.
    • Process Auditing Inspects live processes and installed software lists to identify unauthorized or vulnerable applications.
    • Task Analysis Queries task history to verify previous deployment successes or troubleshoot failed script executions.
    • Remote Execution Runs approved scripts and deploys software packages (install, uninstall, upgrade) on target hosts with system privileges.
    • Credential Security Manages API secrets via the system keychain or encrypted local environment files to avoid chat leaks.

    How it works

    1. Discovery Use action1 lookup commands to identify specific hosts and their current operational state.
    2. Audit Run read-only queries for processes or software to build evidence for a necessary change.
    3. Approval Present the exact script or package action to the user; the agent waits for explicit confirmation before proceeding.
    4. Execution Run the write operation via the CLI with --yes or via the gated MCP tool once an execution token is generated.

    Frameworks & tools

    The skill utilizes the ast-action1 CLI and sectools-mcp server. It requires Python 3.12+ and communicates with the Action1 API (app.action1.com) over HTTPS.

    Why this beats prompting it yourself

    Generic prompts cannot securely interface with RMM APIs or manage the stateful multi-step "dry run to execution" workflow required for Action1 writes. This skill enforces a specific safety protocol that prevents accidental mass-deployments and ensures every system change is logged and pre-approved.

    Use cases

    • Auditing a fleet for a specific vulnerable software version across all online hosts.
    • Remotely reinstalling a corrupted management agent on a specific workstation.
    • Checking live process trees on a host suspected of being compromised.
    • Automating the deployment of emergency patches to a targeted subset of devices.

    Known limitations

    Does not support Intune-managed devices or CrowdStrike Real Time Response. Only supports the app.action1.com data center; other regions are not currently supported. deploy commands do not support winget on macOS or Linux.

    Requires Python 3.12+. Only supports app.action1.com. No support for Intune or CrowdStrike RTR. Software deployment via winget is limited to Windows endpoints.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    Action1
    Python 3.12+
    macOS
    Linux
    Bash 3.2+
    pip
    venv
    Windows
    Python

    Permissions

    Terminal / Shell
    Browser
    Network Access
    Read Files
    Write Files
    Environment Variables

    Allowed Hosts

    app.action1.com

    File Scopes

    ~/.local/share/ast/venv/**
    ~/.config/ast/.env
    ~/.claude/skills/ast-action1/**
    ./.env
    (read
    if
    present)
    ~/Library/Application
    Support/<tool>/.env
    and
    ~/.config/<tool>/.env
    per-tool
    fallback)
    ~/.cache/agentic-security-toolkit/**
    (pending
    dry-run
    /
    exec
    tokens)
    *.json
    *.csv
    at
    a
    path
    you
    choose
    (--output
    sectools_export)

    Terminal/Shell runs `install.sh`, `action1` and `sectools`; Read/Write Files cover the venv, your `~/.config/ast/.env` and optional exports; Environment Variables carry `ACTION1_CLIENT_ID` / `_SECRET`, optional org ID, CrowdStrike CID / maintenance token and the gate; Network Access reaches PyPI at install and `app.action1.com` at run time. Reads (devices, processes, network, software, tasks) change nothing. `run` and `deploy` execute code on the target endpoint as SYSTEM/root: the CLI asks [y/N], MCP exposes them only with `SECTOOLS_ACTION1_EDIT=1`, and the skill requires you to see and approve the exact script or package action and host every time.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill allows you to audit hardware inventory, monitor live processes, and deploy software or scripts directly to Action1 RMM endpoints from your AI agent, eliminating the need to toggle between dashboards.

    The skill includes a built-in safety protocol where every deployment or script execution requires explicit user confirmation and a generated execution token before any changes are applied to production hosts.

    You will need an active Action1 RMM account (app.action1.com region), Python 3.12 or higher, and the `ast-action1` CLI tools to interface with the API securely.

    Currently, this skill is optimized for the Action1 global data center (`app.action1.com`) and does not support other regional data centers or third-party RMMs like Intune.

    Your purchase provides the complete MCP server configuration, the `ast-action1` CLI integration, and detailed documentation for connecting the skill to your existing AI development environment.

    New in APIs & Backend