Medium Risk

cache_decr

Decrement a counter in the cache.

How to control cache_decr ↓

What cache_decr does on Amazon Bedrock Knowledge Base Retrieval MCP Server

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

Medium Risk

Why cache_decr needs a policy

Decrementing a counter modifies existing data in the cache. This is a reversible write operation (the counter can be incremented back), so it falls under Write rather than Destructive. The severity is medium because misuse could corrupt application state or counters that other systems depend on.

From the tool's definition Decrement a counter in the cache

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

How to control cache_decr

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

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

cache_decr 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 Bedrock Knowledge Base Retrieval 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_decr

What does the cache_decr tool do? +

Decrement a counter in the cache. It is categorised as a Write tool in the Amazon Bedrock Knowledge Base Retrieval 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_decr? +

Register the Amazon Bedrock Knowledge Base Retrieval MCP Server MCP server in PolicyLayer and add a rule for cache_decr: 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 Bedrock Knowledge Base Retrieval MCP Server. Nothing to install.

What risk level is cache_decr? +

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

Can I rate-limit cache_decr? +

Yes. Add a rate_limit block to the cache_decr 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_decr completely? +

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

cache_decr is provided by the Amazon Bedrock Knowledge Base Retrieval MCP Server MCP server (awslabs.bedrock-kb-retrieval-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 Bedrock Knowledge Base Retrieval MCP Server tool call.

Start from Amazon Bedrock Knowledge Base Retrieval 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 Bedrock Knowledge Base Retrieval 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.