Atlas / MCP servers / jamesdeane2 / mcp-dattormm

mcp-dattormmSAFE

Name: mcp-dattormm
Author: jamesdeane2

mcp/jamesdeane2/mcp-dattormm

MCP server by jamesdeane2 · active · mcp server · Audited 2026-10-12

⚑ Report / re-scan Source ↗

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

55 40r · 11w · 4d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A comprehensive Model Context Protocol (MCP) server for the Datto RMM API v2. Gives AI assistants like Claude full access to your RMM platform — query devices, manage sites, resolve alerts, run jobs, pull audit data, and control variables, all through natural language.

Features

55 tools covering the full Datto RMM API v2 surface
OAuth 2.0 authentication with automatic token management (100-hour tokens, auto-refresh at 90 hours)
Structured error handling — typed exceptions for auth, validation, rate-limit, not-found, and server errors
Automatic retry with exponential backoff on rate limits (429) and transient server errors (5xx)
Pagination support on all list endpoints (up to 250 results per page)
Modular architecture — one file per API domain, easy to extend
Async throughout — built on httpx with full async/await support

Installation

git clone https://github.com/jamesdeane2/mcp-dattormm.git
cd mcp-dattormm
uv pip install -e .

Configuration

Create a .env file in the project root:

DATTORMM_API_KEY=your-api-key
DATTORMM_API_SECRET=your-api-secret

Getting API Credentials

Read from source at commit 11b2dcb4209cOBSERVED · 2026-10-12

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code

claude mcp add mcp-dattormm -- uvx mcp-dattormm

claude-desktop

{
  "mcpServers": {
    "mcp-dattormm": {
      "command": "uvx",
      "args": [
        "mcp-dattormm"
      ]
    }
  }
}

Exposed tools (55)

40 read · 11 write · 4 destructive. Blast radius: 4 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`dattormm_account_alerts_open`	read	List all open alerts across the account.
`dattormm_account_alerts_resolved`	read	List all resolved alerts across the account.
`dattormm_account_components`	read	List available components (scripts/monitors) in the account.
`dattormm_account_devices`	read	List all devices in the account with optional filters.
`dattormm_account_dnet_mappings`	read	Get Datto Networking site mappings.
`dattormm_account_get`	read	Get account details.
`dattormm_account_sites`	read	List all sites in the account.
`dattormm_account_users`	read	List all users in the account.
`dattormm_account_variable_create`	write	Create a new account-level variable.
`dattormm_account_variable_delete`	destructive	Delete an account-level variable.
`dattormm_account_variable_update`	write	Update an existing account-level variable.
`dattormm_account_variables`	read	List all account-level variables.
`dattormm_activity_logs`	read	Get activity logs with optional filters.
`dattormm_alert_get`	read	Get alert details by UID.
`dattormm_alert_resolve`	read	Resolve an open alert.
`dattormm_audit_device`	read	Get full audit data for a device.
`dattormm_audit_device_by_mac`	read	Get audit data for a device by MAC address.
`dattormm_audit_device_software`	read	Get software inventory for a device.
`dattormm_audit_esxi`	read	Get ESXi host audit data.
`dattormm_audit_printer`	read	Get printer audit data for a device.
`dattormm_device_alerts_open`	read	List open alerts for a device.
`dattormm_device_alerts_resolved`	read	List resolved alerts for a device.
`dattormm_device_get`	read	Get device details by UID.
`dattormm_device_get_by_id`	read	Get device details by numeric ID.
`dattormm_device_get_by_mac`	read	Get device details by MAC address.
`dattormm_device_move`	write	Move a device to a different site.
`dattormm_device_quickjob`	write	Run a quick job (component) on a device.
`dattormm_device_udf_set`	write	Set user defined fields (UDF) on a device.
`dattormm_device_warranty_set`	write	Set warranty information on a device.
`dattormm_filters_custom`	read	List all custom (user-created) device filters.
`dattormm_filters_default`	read	List all default (built-in) device filters.
`dattormm_job_components`	read	Get components associated with a job.
`dattormm_job_get`	read	Get job details by UID.
`dattormm_job_results`	read	Get job results for a specific device.
`dattormm_job_stderr`	read	Get stderr output from a job execution on a device.
`dattormm_job_stdout`	read	Get stdout output from a job execution on a device.
`dattormm_site_alerts_open`	read	List open alerts for a site.
`dattormm_site_alerts_resolved`	read	List resolved alerts for a site.
`dattormm_site_create`	write	Create a new site.
`dattormm_site_devices`	read	List all devices at a site.
`dattormm_site_devices_network`	read	List network interface information for all devices at a site.
`dattormm_site_filters`	read	List filters available for a site.
`dattormm_site_get`	read	Get site details by UID.
`dattormm_site_proxy_delete`	destructive	Delete proxy settings for a site.
`dattormm_site_proxy_update`	write	Update proxy settings for a site.
`dattormm_site_settings`	read	Get site settings.
`dattormm_site_update`	write	Update an existing site.
`dattormm_site_variable_create`	write	Create a new site-level variable.
`dattormm_site_variable_delete`	destructive	Delete a site-level variable.
`dattormm_site_variable_update`	write	Update an existing site-level variable.
`dattormm_site_variables`	read	List all site-level variables.
`dattormm_system_pagination`	read	Get pagination settings for the API.
`dattormm_system_rate`	read	Get current API request rate information.
`dattormm_system_status`	read	Get current system status.
`dattormm_user_reset_api_keys`	destructive	Reset the API keys for the current user.

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (1 observation(s))
Network: declared (4 observation(s))
Shell: none-observed
Dependencies: pinned
Secrets in source: none-found

Findings (2)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

dattormm_account_variable_delete, dattormm_site_proxy_delete, dattormm_site_variable_delete, dattormm_user_reset_api_keys

Why it matters. 4 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427

README.md:8

A comprehensive [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) server for the [Datto RMM](https://www.datto.com/products/rmm/) API v2. Gives AI assistants like Claude full access to

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 11b2dcb4209cfull audit observations/trust-audit/mcp-server/jamesdeane2__mcp-dattormm.json · Report an issue / request a re-scan

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

Date	Source	Verdict	Grade	Score	Change
2026-10-12	`11b2dcb4209c`	SAFE	B	89	first audit

Questions

What tools does mcp-dattormm expose?

55 in total: 40 read-only, 11 that write, and 4 that can delete or overwrite (dattormm_account_variable_delete, dattormm_site_proxy_delete, dattormm_site_variable_delete, dattormm_user_reset_api_keys). Every one is listed on this page with its risk.

Is mcp-dattormm safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 4 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does mcp-dattormm need?

No credential environment variables were found in its source, so it appears to need none.

How does mcp-dattormm run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-dattormm.

How current is this page?

The grade is for one exact copy of the source (11b2dcb4209c), read on 2026-10-12. The repository is watched and re-audited when it changes.

Source	jamesdeane2/mcp-dattormm
PyPI	`mcp-dattormm`
Transports	stdio
License	MIT
Activity	pushed 10d ago