// SCAN REPORT

Avalanche

16 tools. 8 can modify or destroy data without limits.

8 write tools that can modify data. Rate limits recommended.

Last updated: 12 Aug 2026

8 can modify or destroy data

8 read-only

16 tools total

Community server · catalogue entry checked 05/08/2026

How to control Avalanche ↓

TOOL MAP

What Avalanche exposes to your agents

Read (8) Write / Execute (8) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Avalanche tools

Execute · High deploy_contract Deploys smart contracts to blockchain networks, triggering irreversible state changes and potential financial exposure on mainnet. Execute · High devnet_launch_l1 Launches and deploys blockchain infrastructure locally; triggers external operations with broad side effects. Execute · High devnet_spin_up Launches and deploys blockchain infrastructure locally with irreversible network state changes and relayer setup. Execute · High devnet_start Initiates a network service whose side effects depend on system state and configuration.

8 of Avalanche's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Avalanche

PolicyLayer is an MCP gateway — it sits between your AI agents and Avalanche, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "scaffold_app": {
    "limits": [
      {
        "counter": "scaffold_app_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "avalanche_env": {
    "limits": [
      {
        "counter": "avalanche_env_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Avalanche — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AVALANCHE →

Instant setup, no code required.

FULL CATALOGUE

All 16 Avalanche tools

EXECUTE 7 tools

Execute deploy_contract Deploy compiled bytecode to Avalanche using a deployer key from the AVAKIT_DEPLOYER_KEY env var. Fuji testnet Execute devnet_launch_l1 Create a single custom Subnet-EVM L1 and deploy it locally. Returns the exit code and log tail; read the chain Execute devnet_spin_up Create two local Avalanche L1s with Interchain Messaging and a relayer, and deploy them locally. Idempotent. T Execute devnet_start Start the local Avalanche network. Execute devnet_stop Stop the local Avalanche network. Execute icm_deploy_messengers Deploy the AvaKitMessenger contract on each running L1 that doesn Execute icm_send Send a string from one L1

WRITE 1 tools

Write scaffold_app Create a new Avalanche dapp from a template (minimal, nft-mint, token-gated-app, erc20-token, icm-messenger, e

READ 8 tools

Read avalanche_env Detect the local Avalanche toolchain (avalanche-cli, Foundry), the current project, and any local L1s. Read data_lookup Balances, NFTs, and recent transactions for an address on a public Avalanche chain, via the AvaCloud Data API. Read devnet_status Report the local L1s and whether the local network is running. Read estimate_gas Estimate the gas a transaction (to / data / value) would use and report the current gas price and rough AVAX c Read get_context Return AvaKit + Avalanche context for coding: the API surface, conventions, and doc links. Read icm_state Report each L1 Read list_templates List the Avalanche dapp templates available to scaffold_app. Read read_chain Read a native AVAX balance, a transaction receipt, or a contract view/pure function over RPC.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Avalanche

How do I prevent bulk modifications through Avalanche? +

The Avalanche server has 1 write tools including scaffold_app. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Avalanche.

How many tools does the Avalanche MCP server expose? +

16 tools across 3 categories: Execute, Read, Write. 8 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Avalanche? +

Register the Avalanche MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Avalanche tool call.

Deterministic rules across all 16 Avalanche tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AVALANCHE →

Instant setup, no code required.

16 Avalanche tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Avalanche's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →