AI agents use cache_incr to create or update resources in Amazon ECS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Amazon ECS MCP Server environment.
Incrementing a counter modifies existing data in the cache (a write operation). It's reversible in principle (the counter can be decremented or reset). The mismatch between the tool's purpose (cache counter increment) and the server's stated focus (AWS ECS containerization/deployment) is suspicious and lowers confidence. Misuse could affect application logic relying on cache counters, giving it medium severity.
From the tool's definition Increment a counter in the cache
Documented attack patterns abuse exactly the kind of access cache_incr gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Amazon ECS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cache_incr:
{
"version": "1",
"default": "deny",
"tools": {
"cache_incr": {
"limits": [
{
"counter": "cache_incr_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}cache_incr 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.
Free to start. No card required.
Increment a counter in the cache. It is categorised as a Write tool in the Amazon ECS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Amazon ECS MCP Server MCP server in PolicyLayer and add a rule for cache_incr: 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 ECS MCP Server. Nothing to install.
cache_incr is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cache_incr 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.
Set action: deny in the PolicyLayer policy for cache_incr. 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.
cache_incr is provided by the Amazon ECS MCP Server MCP server (awslabs.ecs-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Amazon ECS 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 ECS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.