icm_send

Send a string from one L1

SERVERAvalanche SOURCE@avakit/mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

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

WHAT IT DOES

What icm_send does on Avalanche

AI agents invoke icm_send to trigger actions in Avalanche. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why icm_send is rated High

Triggers cross-chain message transmission, an external blockchain operation with irreversible effects.

From the tool's definition Send a string from one L1

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs icm_send 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_send, this is the rule to start with:

icm_send Rate-limited

icm_send stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "icm_send": {
      "limits": [
        {
          "counter": "icm_send_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about icm_send

What does the icm_send tool do? +

Send a string from one L1. It is categorised as a Execute tool in the Avalanche MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on icm_send? +

Register the Avalanche MCP server in PolicyLayer and add a rule for icm_send: 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_send? +

icm_send is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit icm_send? +

Yes. Add a rate_limit block to the icm_send 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_send completely? +

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

icm_send 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 → High-risk tools on this server →

Across the catalogue

send_key_to_window on Frida Game Hacking MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →