Medium Risk

cache_replace

Replace a value in the cache only if the key exists.

How to control cache_replace ↓

What cache_replace does on Awslabs Amazon Sns Sqs

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

Medium Risk

Why cache_replace needs a policy

This tool modifies cached data reversibly without deleting or destroying it. It is a write operation that changes an existing value. Severity is medium because cache corruption could disrupt application behavior and messaging service operations, but the blast radius is limited to cache state rather than persistent data or message queues themselves.

From the tool's definition Tool description states 'Replace a value in the cache' which is a modification operation. The conditional 'only if the key exists' indicates idempotent semantics but does not prevent the write operation.

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

How to control cache_replace

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

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

cache_replace 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 Awslabs Amazon Sns Sqs — 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_replace

What does the cache_replace tool do? +

Replace a value in the cache only if the key exists. It is categorised as a Write tool in the Awslabs Amazon Sns Sqs 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_replace? +

Register the Awslabs Amazon Sns Sqs MCP server in PolicyLayer and add a rule for cache_replace: 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 Awslabs Amazon Sns Sqs. Nothing to install.

What risk level is cache_replace? +

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

Can I rate-limit cache_replace? +

Yes. Add a rate_limit block to the cache_replace 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_replace completely? +

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

cache_replace is provided by the Awslabs Amazon Sns Sqs MCP server (awslabs.amazon-sns-sqs-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 Awslabs Amazon Sns Sqs tool call.

Start from Awslabs Amazon Sns Sqs, 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 Awslabs Amazon Sns Sqs 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.