icm_state

Report each L1

SERVERAvalanche SOURCE@avakit/mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/dev-avakit-avalanche/icm-state.md

WHAT IT DOES

What icm_state does on Avalanche

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

RISK

Why icm_state is rated Low

Tool reports state information about L1s, a read-only operation.

From the tool's definition Report each L1

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs icm_state safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Avalanche, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For icm_state, this is the rule to start with:

icm_state Allowed

icm_state is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "icm_state": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Avalanche, apply this rule, and every icm_state call is checked against it from then on.

FAQ

Questions about icm_state

What does the icm_state tool do? +

Report each L1. It is categorised as a Read tool in the Avalanche MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on icm_state? +

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

What risk level is icm_state? +

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

Can I rate-limit icm_state? +

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

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

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

KEEP EXPLORING

More on Avalanche, and thousands of servers like it.

This server

All 16 Avalanche tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →