cache_flush_all

THE RISK

Critical Risk

Why cache_flush_all needs a policy

Flushing all cache entries is an irreversible bulk operation — once evicted, cached data is gone and cannot be restored. This qualifies as Destructive with high severity because misuse by an AI agent would instantly wipe all cached data, potentially causing cascading failures, increased latency, or data loss depending on the cache's role in the system.

From the tool's definition Flush all cache entries

Risk signalsBulk/mass operation — affects multiple targets

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

POLICY

How to control cache_flush_all

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

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "cache_flush_all"
  ]
}

cache_flush_all disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register AWS — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More AWS tools

Destructive bulk_delete_by_criteria bulk_delete_by_criteria Destructive cache_delete Delete a value from the cache. Args: key: The key to delete Returns: Destructive cache_delete_many Delete multiple values from the cache. Args: keys: List of keys to delete Destructive cache_delete_multi Delete multiple values from the cache (alias for delete_many). Args: keys: Li Destructive delete Delete a Valkey key. Args: key (str): The key to delete. Returns: Destructive delete_access_key delete_access_key Destructive delete_datastore Delete a data store from AWS HealthImaging. Destructive delete_group delete_group

All 300 AWS tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Govern infrastructure agents → Production lockdown, region locks, and approval-to-delete on every infrastructure call agents make.
Critical-risk tools in AWS → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →
PolicyLayer vs alternatives → How deterministic, per-call MCP policy compares with gateways, identity layers, and authorisation platforms.

FAQ

Questions about cache_flush_all

What does the cache_flush_all tool do? +

Flush all cache entries. Args: delay: Optional delay in seconds before flushing Returns: Success message or error message. It is categorised as a Destructive tool in the AWS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on cache_flush_all? +

Register the AWS MCP server in PolicyLayer and add a rule for cache_flush_all: 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 AWS. Nothing to install.

What risk level is cache_flush_all? +

cache_flush_all is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit cache_flush_all? +

Yes. Add a rate_limit block to the cache_flush_all 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_flush_all completely? +

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

cache_flush_all is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AWS tool call.

Start from AWS, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →