ThreatLocker MCP

ThreatLocker + AI - for Claude, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, and any agent that speaks MCP

Unofficial. Community-built Claude Code Skill and MCP server for the ThreatLocker API. Not affiliated with, endorsed by, or sponsored by ThreatLocker, Inc..

[ThreatLocker - MCP server and Claude Code Skill]

_{Full skill page - install, outcomes, safety model.}

Every ThreatLocker Portal API feature, plus the write operations the read-only tools lack and a cross-tenant offline store no other ThreatLocker tool has. Works with the AI you already use - ChatGPT (desktop app), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Gemini CLI. Free, open source, runs on your laptop. Built for MSP owners. No code required.

Works with your agent

The six agents MSP owners actually use (self-serve, works today):

The ChatGPT desktop app runs threatlocker-mcp locally and shares MCP configuration with Codex (OpenAI). ChatGPT on the web needs a remote server, which msp-skills does not support yet. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list. Setup steps: mcp-install.md.

Also for the Microsoft and Google stacks

Big install base, but an honest heads-up: Gemini CLI runs the local binary you just installed, while Microsoft 365 Copilot and the Gemini app need a remote server, which msp-skills does not support yet.

Skill-native agents (also covered): Hermes and OpenClaw read this skill's SKILL.md directly and speak MCP - see their install sections below. Also works with Cursor, Windsurf, Cline, Continue.dev, and Zed via MCP. Full per-tool wire-up: docs/which-agent.md.

Run more than one agent? Install across all 51+ supported agents in one command: npx skills add Servosity/msp-skills@latest (requires Node.js, then run the per-skill installer for the CLI/MCP binaries). See docs/which-agent.md.

Install in 60 seconds

Fastest for Claude Desktop - one-click .mcpb

Claude Desktop bundle: the .mcpb launches on macOS (Intel and Apple Silicon), Windows x64 and Linux x64. Every tool shells out to the companion threatlocker-cli. Releases cut from 2026-09-18 on ship that CLI inside the bundle; older bundles contain only the MCP server, so if yours lacks the companion, run the Path A or Path B installer below first (or set THREATLOCKER_CLI_PATH to an existing binary). Details: #331.

Download ThreatLocker MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every ThreatLocker release on the releases page.)

Prefer the Claude Code plugin? Add the marketplace once, then install - works immediately, no directory listing required:

/plugin marketplace add Servosity/msp-skills/plugin install threatlocker@msp-skills

Path A - paste one prompt into your AI agent (recommended)

Copy this into Claude Code, Codex CLI, or Claude Cowork:

Install the ThreatLocker Skill and MCP server from Servosity/msp-skills in this agent workspace. If this workspace uses a POSIX shell (macOS, Linux, WSL, or Bash), run bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/threatlocker/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/threatlocker/install.ps1 | iex. Then authenticate per the README and run threatlocker-cli --help to explore.

The same prompt works in any agent that can run shell.

Path B - run the installer yourself

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/threatlocker/install.ps1 | iex

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/threatlocker/install.sh)

The installer drops both threatlocker-cli (the CLI) and threatlocker-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.

Verify:

threatlocker-cli --version

Upgrade to the latest version

The installer always fetches the current release - re-run it to upgrade:

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/threatlocker/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/threatlocker/install.ps1 | iex

Claude Desktop .mcpb users: download the latest .mcpb (top of this section) and re-select it in Settings > Extensions. Claude Code plugin users: /plugin update threatlocker@msp-skills.

Add to Claude Desktop, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, or another MCP client

After the installer runs, see mcp-install.md and docs/which-agent.md for the per-agent wire-up - one section per agent, including the GitHub Copilot servers key and the ChatGPT desktop app. Claude Desktop's Settings > Extensions panel is the simplest path; the MCP config block (for users who prefer editing JSON) is documented in mcp-install.md.

Install for Hermes

From the Hermes CLI:

hermes skills install servosity/msp-skills/skills/threatlocker --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/threatlocker --force

Hermes speaks MCP natively, so it can also use the threatlocker-mcp server directly - same install path, same env vars.

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the threatlocker skill from https://github.com/servosity/msp-skills/tree/main/skills/threatlocker. The skill defines how its required CLI (threatlocker-cli) can be installed via the openclaw: frontmatter block.

OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.

Authenticate

Set the credentials the CLI needs (from your ThreatLocker portal):

THREATLOCKER_API_KEY=<value> threatlocker-cli doctor

doctor confirms the credentials work before you run anything that touches data. It exits 0 even when the credential is rejected, so scripts should add --fail-on error.

What this skill does

The audit rows read what audit pull saved, and the other rows read what sync saved: run threatlocker-cli sync and threatlocker-cli audit pull --since 30d first, and keep audit pull on a schedule shorter than 31 days.

Full command reference: guide.md. For the AI-agent operating contract (--agent, --dry-run, when to confirm before mutating), see AGENTS.md.

What makes this different

Most ThreatLocker integrations and MCP servers proxy each question into a live API call. That's fine for one record. It dies at scale, because the Portal API is scoped one tenant at a time, so asking "show me every pending approval across all 40 clients, deduped by file hash" or "which clients are about to lose audit evidence this month" turns into a header-swap-and-re-query dance the AI burns context on, tenant by tenant.

This skill syncs ThreatLocker into a local SQLite mirror with full-text search. Aggregate questions become one local SQL join: instant, offline, and the AI sees the answer, not the raw data. Compound commands like approvals triage, applications hunt, and devices health join approval requests, applications, computers, and audit events across every tenant at once - work a stateless API wrapper can't do.

The pain this closes

ThreatLocker is default-deny, so every new or updated application becomes an approval request an admin has to clear. ThreatLocker's own MSP guide admits the volume: "While you are onboarding your first few clients, your devices are learning and can be quite noisy" (Allowlisting for MSPs). Across a book of tenants the queue never goes quiet, and the Portal makes you clear it one tenant at a time. Then there's evidence: ThreatLocker's Help Center is explicit that "by default, the Unified Audit retains data for 31 days. After 31 days, the information is permanently deleted and cannot be recovered" (Log Retention) - shorter than most compliance and cyber-insurance asks.

This skill closes both:

• approvals triage --all-tenants - one ranked queue of every pending approval across all tenants, deduped by file hash.
• approvals approve-batch --hash <sha256> --all-tenants --dry-run - permit a known-good file everywhere it's pending, plan first; the live run needs --yes.
• audit pull --since 30d + audit retention-check - save every tenant's deny events locally before evidence ages off (--action permit adds permitted events), and flag tenants near the 31-day cliff; audit export hands the saved log to a SIEM or an auditor.
• devices health --all-tenants - surface dark and stale agents across the whole book without a tenant-by-tenant sweep.

See pain-point.md for the longer narrative.

Frequently asked questions

Does this work with ChatGPT?

Yes, in the ChatGPT desktop app. It runs MCP servers locally (STDIO), the way threatlocker-mcp runs, and shares MCP configuration with Codex (OpenAI): add threatlocker-mcp under Settings > MCP servers as a STDIO server, or add it once to Codex's ~/.codex/config.toml. ChatGPT on the web is not supported by msp-skills yet: it needs a remote server. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list. Setup steps: mcp-install.md.

Does this work with Codex, Cursor, Windsurf, Cline, Copilot, or Gemini?

Yes - all of them speak MCP. Cross-tool install commands are in the matrix above and the deep-dive in docs/which-agent.md.

Do I need to know how to code?

No. The recommended install is to paste one sentence into Claude Code or Codex - your agent reads SKILL.md and does the install. The fallback is a one-line installer per OS (bash or PowerShell). Neither path requires writing code. You'll enter your ThreatLocker credentials once.

Is my ThreatLocker data safe?

Your data stays on your machine. The CLI and MCP server are local binaries. The SQLite mirror sits in a directory under your user account. The AI agent only sees what the CLI returns - typically a query result, not raw bulk data. Credentials are read from your environment or your agent's config; never bundled into this repo or transmitted anywhere by MSP Skills.

Will this hit my ThreatLocker API rate limits?

The local mirror exists so reads stop hitting the API. After the first sync, the cross-tenant views (approvals triage, audit drift, devices health, applications hunt) run against local SQLite with zero API calls. Live calls respect a --rate-limit throttle, and sync is incremental, fetching only what changed since the last checkpoint.

How does it handle ThreatLocker's 31-day audit retention?

ThreatLocker's Unified Audit log keeps about 31 days by default. audit pull saves each tenant's deny events (or, with --action permit, permitted ones) to the local store so the evidence outlives that window, audit export writes it out as JSONL or CSV, and audit retention-check reports, per tenant, how close your archive is to the cliff and how stale your last sync is, so nothing ages off unnoticed.

Do I need to be a ThreatLocker MSP or have child tenants?

You need API access in your own ThreatLocker Portal. The cross-tenant features assume a managed (parent) organization with child tenants, the MSP setup, but a single organization works too, you just get the one-tenant view. The credential you mint is the real permission boundary.

Does it replace the ThreatLocker Portal?

No. The Portal stays best for authoring policies and the interactive approve/deny workflow. This skill adds cross-tenant queries and scriptable writes to your AI agent so you stop logging into each tenant to answer book-wide questions.

What does it cost?

Free. Apache-2.0 licensed. You pay only for whichever AI agent you use (Claude, ChatGPT, Codex, etc.), and that's billed by your AI provider, not by us.

Safety model

The strongest control is the scope you grant the ThreatLocker credentials - the CLI can only do what the credentials are permitted to do. Full details, including how to lock it down, are in governance.md.

Status

Live-verified. Confirmed by @geekbrownbear (MSP) against their own production tenant (receipt). More MSPs run it live in our weekly Build Sessions. RSVP at compoundingteams.com/build-sessions.

Standards. Conforms to the open Agent Skills spec (Anthropic, Dec 2025; 40+ agents). MCP-compatible - works with any MCP-capable agent including Hermes. OpenClaw-ready (frontmatter pre-wired, awaiting OpenClaw launch).

Maintained by Servosity. Apache-2.0 licensed. Built with CLI Printing Press. Last updated: 2026-06-05.