Low Risk

get_alerts

Get weather alerts for a state. Returns JSON with features array containing alert objects. Each alert has properties: { event, severity, areaDesc, headline, description, instruction, effective, expires, ends }. Severity levels: Extreme, Severe, Moderate, Minor.

How to control get_alerts ↓

What get_alerts does on Codemesh

AI agents call get_alerts to retrieve information from Codemesh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why get_alerts needs a policy

This tool retrieves and returns weather alert information without creating, modifying, deleting, or executing any operations. It has a Read pattern (fetch/retrieve data). Severity is low because misuse would only expose informational weather data with no destructive, financial, or system-level consequences.

From the tool's definition Tool name 'get_alerts' and description indicate it 'Get weather alerts for a state. Returns JSON with features array containing alert objects.' The operation is purely retrieval of pre-existing weather alert data with no side effects, modifications, or…

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

How to control get_alerts

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_alerts": {}
  }
}

get_alerts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Codemesh — 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.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about get_alerts

What does the get_alerts tool do? +

Get weather alerts for a state. Returns JSON with features array containing alert objects. Each alert has properties: { event, severity, areaDesc, headline, description, instruction, effective, expires, ends }. Severity levels: Extreme, Severe, Moderate, Minor. It is categorised as a Read tool in the Codemesh MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_alerts? +

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

What risk level is get_alerts? +

get_alerts is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_alerts? +

Yes. Add a rate_limit block to the get_alerts 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 get_alerts completely? +

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

get_alerts is provided by the Codemesh MCP server (kiliman/codemesh). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Codemesh tool call.

Start from Codemesh, 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.

13 Codemesh 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.