Medium Risk

cache_add

Add a value to the cache only if the key doesn't exist.

How to control cache_add ↓

What cache_add does on Amazon Translate MCP Server

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

Medium Risk

Why cache_add needs a policy

The tool creates or modifies cache entries, which is reversible (values can be updated or deleted). It does not retrieve data (Read), execute code (Execute), permanently delete data (Destructive), move money (Financial), or fall into other categories. The low severity reflects that cache operations typically have limited blast radius and can be recovered from.

From the tool's definition Tool description explicitly states 'Add a value to the cache' - a create/modify operation that modifies cache state. The conditional 'only if the key doesn't exist' indicates idempotent semantics but still constitutes a write operation.

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

How to control cache_add

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

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

cache_add 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 Amazon Translate 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 cache_add

What does the cache_add tool do? +

Add a value to the cache only if the key doesn't exist. It is categorised as a Write tool in the Amazon Translate 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 cache_add? +

Register the Amazon Translate MCP Server MCP server in PolicyLayer and add a rule for cache_add: 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 Amazon Translate MCP Server. Nothing to install.

What risk level is cache_add? +

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

Can I rate-limit cache_add? +

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

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

cache_add is provided by the Amazon Translate MCP Server MCP server (awslabs.amazon-translate-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 Amazon Translate MCP Server tool call.

Start from Amazon Translate 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.

805 Amazon Translate 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.