get_user_grants

THE RISK

Low Risk

Why get_user_grants needs a policy

This tool retrieves access control and permission information about users in the Linode infrastructure. While it is read-only (no data is modified), the sensitivity of the data returned (user grants/permissions) elevates severity from low to medium, as exposure of access control details could aid privilege escalation attacks or inform social engineering.

From the tool's definition Tool name 'get_user_grants' indicates retrieval of user permission/access data. Description states '[DEPRECATED] Get a user' suggesting it queries user grant information without modification.

Documented attack patterns abuse exactly the kind of access get_user_grants gives an agent:

POLICY

How to control get_user_grants

PolicyLayer is an MCP gateway — it sits between your AI agents and Linode MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_user_grants:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_user_grants": {}
  }
}

get_user_grants is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Linode MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Linode MCP Server tools

Destructive cancel_account Cancel your account Destructive cancel_backups Cancel backups for a Linode instance Destructive cancel_object_storage Cancel Object Storage service Destructive delete_alert_definition Delete an alert definition Destructive delete_api_token Delete an API token Destructive delete_config_interface Delete an interface from a configuration profile Destructive delete_domain Delete a domain Destructive delete_domain_record Delete a domain record

All 416 Linode MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_user_grants

What does the get_user_grants tool do? +

[DEPRECATED] Get a user\. It is categorised as a Read tool in the Linode MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_user_grants? +

Register the Linode MCP Server MCP server in PolicyLayer and add a rule for get_user_grants: 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 Linode MCP Server. Nothing to install.

What risk level is get_user_grants? +

get_user_grants is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_user_grants? +

Yes. Add a rate_limit block to the get_user_grants 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.

How do I block get_user_grants completely? +

Set action: deny in the PolicyLayer policy for get_user_grants. 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.

What MCP server provides get_user_grants? +

get_user_grants is provided by the Linode MCP Server MCP server (takashito/linode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Linode MCP Server tool call.

Start from Linode MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →