Medium Risk

liara_resize_database

Change database plan (resize resources)

How to control liara_resize_database ↓

What liara_resize_database does on Liara MCP Server

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

Medium Risk

Why liara_resize_database needs a policy

This tool modifies infrastructure configuration by changing database resource allocation. While the change is reversible (can be resized again), it materially alters the state of a critical system dependency. The severity is high because misconfigured database sizing can cause service degradation or downtime, and the action has cloud infrastructure blast radius.

From the tool's definition Tool name 'liara_resize_database' with description 'Change database plan (resize resources)' indicates modification of existing infrastructure configuration.

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

How to control liara_resize_database

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

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

liara_resize_database 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 Liara 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 liara_resize_database

What does the liara_resize_database tool do? +

Change database plan (resize resources). It is categorised as a Write tool in the Liara 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 liara_resize_database? +

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

What risk level is liara_resize_database? +

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

Can I rate-limit liara_resize_database? +

Yes. Add a rate_limit block to the liara_resize_database 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 liara_resize_database completely? +

Set action: deny in the PolicyLayer policy for liara_resize_database. 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 liara_resize_database? +

liara_resize_database is provided by the Liara MCP Server MCP server (razavioo/liara-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Liara MCP Server tool call.

Start from Liara 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.

108 Liara 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.