AI agents use user_settings to create or update resources in Microsoft Graph MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Microsoft Graph MCP Server environment.
This tool modifies user configuration data reversibly. While the description is incomplete (it mentions "two actions" without specifying them), the use of "manage" in a settings context typically means create/update operations rather than read-only access. Settings changes can have broad impact on system behavior and user workflows, warranting high severity.
From the tool's definition Tool description explicitly states "Manage user settings with two actions" - the verb "manage" combined with "settings" indicates modification capabilities.
Documented attack patterns abuse exactly the kind of access user_settings gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Microsoft Graph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for user_settings:
{
"version": "1",
"default": "deny",
"tools": {
"user_settings": {
"limits": [
{
"counter": "user_settings_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} user_settings stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Manage user settings with two actions:. It is categorised as a Write tool in the Microsoft Graph MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Microsoft Graph MCP Server MCP server in PolicyLayer and add a rule for user_settings: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Microsoft Graph MCP Server. Nothing to install.
user_settings is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the user_settings rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for user_settings. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
user_settings is provided by the Microsoft Graph MCP Server MCP server (marlonluo2018/microsoft_graph_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Microsoft Graph MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 Microsoft Graph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.