AI agents use cache_set to create or update resources in Prometheus MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prometheus MCP Server environment.
This tool writes data to a cache system, which is a reversible operation (cached values can be updated or invalidated). It does not execute arbitrary code, delete data permanently, or move financial resources. However, depending on what data is cached and how it's used downstream, poisoned cache values could affect system behavior, warranting medium severity.
From the tool's definition Tool name 'cache_set' and description 'Set a value in the cache' indicate creating or modifying cached data.
Documented attack patterns abuse exactly the kind of access cache_set gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Prometheus MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cache_set:
{
"version": "1",
"default": "deny",
"tools": {
"cache_set": {
"limits": [
{
"counter": "cache_set_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}cache_set 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.
Set a value in the cache. It is categorised as a Write tool in the Prometheus MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Prometheus MCP Server MCP server in PolicyLayer and add a rule for cache_set: 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 Prometheus MCP Server. Nothing to install.
cache_set 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_set 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_set. 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_set is provided by the Prometheus MCP Server MCP server (awslabs.prometheus-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Prometheus 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 Prometheus MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.