Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@trmm-action-mcp Run the local_admins audit on agent 'WS-SALES-04'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A gated, allow-listed action server for Tactical RMM. Unlike the read-only
trmm-mcp server, this one can act on endpoints — but only
by running a vetted, read-only audit from a fixed catalog. There is
deliberately no tool to run arbitrary code and no tool to delete, edit,
reboot, or uninstall anything.
Built for a small group of senior engineers (e.g. the approved engineers) to run audits like "list Domain Admins on EF-DC01" from Claude.
Identity — reachable only by the named senior engineers.
Network — nginx allows only Anthropic's connector egress IPs (+ your IPs).
Bearer — shared secret between the edge and this backend.
Restricted tools — only list_agents, list_audits, run_audit.
Allow-listed audits — run_audit runs only vetted read-only scripts in
catalog.py; no arbitrary-code path exists.
Scoped TRMM key — the claude-actions role can
Send-Command + read, nothing else. Every run is TRMM-audit-logged.
"Can't delete stuff" is a guarantee here (allow-listed catalog + no delete tools +
scoped key), not a hope — see the note in catalog.py.
Related MCP server: firewalla-mcp-server
Tool | Kind | What it does |
| read | Find the agent to target (filter by client/site/type/platform/status/hostname). |
| read | The catalog of runnable audits (the only scripts |
| action | Run ONE vetted audit on ONE agent; returns its output. |
privileged_groups (DC), local_admins, local_users, disk_space, os_info,
installed_software, services_not_running, pending_reboot, hotfixes,
logged_on_users, bitlocker, network_config. All read-only. Add more by
vetting a new entry in catalog.py.
Variable | Required | Description |
| ✅ | TRMM API base URL ( |
| ✅ | The scoped |
| — |
|
| http only | Shared bearer between edge and backend. |
| — | Default |
| — | Tuning. |
python -m venv .venv && .venv\Scripts\activate # or source .venv/bin/activate
pip install -r requirements.txt
# stdio (local dev): set TRMM_API_URL + TRMM_ACTION_API_KEY, then:
python -m trmm_action_mcpSee docs/DEPLOY.md (Docker + nginx Anthropic-IP allowlist + identity options) and docs/TRMM_ROLE.md (the scoped key). The senior-engineer path that works today is Claude Code/Desktop + bearer behind the nginx allowlist; per-user Entra SSO for claude.ai web/mobile is best done via Cloudflare Access (see the read-only project) — DEPLOY.md explains the trade-offs.
Separate project, separate key, separate deploy on purpose: the read-only server stays incapable of acting, and this one stays incapable of anything but vetted audits.
This server cannot be deployed
Run verified read-only code tools: quant diagnostics + agent-ops preflight, no source exposure.
Read-only MCP access to a documented IT fleet: state, changes, posture. 15 tools.
Read-only finance and operations controls for AI agents with evidence and safe next actions.
Your audit methodology inside Claude: findings, risks, controls and workpapers in your team format.
