AI agents call get_silence to retrieve information from Alertmanager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves silence configuration data from AlertManager by ID. It performs a read-only query operation without modifying, deleting, or executing any actions. The blast radius of misuse is minimal—an attacker could only view existing silence rules, not create, modify, or delete them.
From the tool's definition Tool name is 'get_silence' and description states 'Get a silence by its ID', indicating a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_silence gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Alertmanager, and nothing reaches the server without passing your rules. This is the rule we recommend for get_silence:
{
"version": "1",
"default": "deny",
"tools": {
"get_silence": {}
}
}get_silence is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a silence by its ID. It is categorised as a Read tool in the Alertmanager MCP Server, which means it retrieves data without modifying state.
Register the Alertmanager MCP server in PolicyLayer and add a rule for get_silence: 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 Alertmanager. Nothing to install.
get_silence is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_silence 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 get_silence. 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.
get_silence is provided by the Alertmanager MCP server (ntk148v/alertmanager-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Alertmanager, 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.
9 Alertmanager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.