Medium Risk

update_user_grants

[DEPRECATED] Update a user\

How to control update_user_grants ↓

What update_user_grants does on Linode MCP Server

AI agents use update_user_grants to create or update resources in Linode MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Linode MCP Server environment.

Medium Risk

Why update_user_grants needs a policy

This tool modifies user access permissions and grants, which is a reversible write operation on sensitive security configuration. It could allow an AI agent to elevate privileges or modify access controls if misused. High severity due to security implications of unintended access control changes, though marked DEPRECATED so actual risk may be lower in practice.

From the tool's definition Tool name 'update_user_grants' and description 'Update a user' indicate modification of user permissions/access control settings. The ability to modify user grants is a write operation that affects authentication and authorization state.

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

How to control update_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 update_user_grants:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_user_grants": {
      "limits": [
        {
          "counter": "update_user_grants_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

update_user_grants 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.

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

Free to start. No card required.

Related tools and policies

Go deeper

Questions about update_user_grants

What does the update_user_grants tool do? +

[DEPRECATED] Update a user\. It is categorised as a Write tool in the Linode MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_user_grants? +

Register the Linode MCP Server MCP server in PolicyLayer and add a rule for update_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 update_user_grants? +

update_user_grants is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_user_grants? +

Yes. Add a rate_limit block to the update_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 update_user_grants completely? +

Set action: deny in the PolicyLayer policy for update_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 update_user_grants? +

update_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.

Free to start. No card required.

416 Linode MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.