// SCAN REPORT

Avalanche AVAX MCP

44 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 6 Jun 2026

0 can modify or destroy data

44 read-only

44 tools total

Free to start. No card required.

TOOL MAP

Read (44) Write / Execute (0) Destructive / Financial (0)

CONTEXT-WINDOW COST

4,415 tokens of tool definitions, loaded on every request

2.2% of a 200k context window

251 heaviest tool: github_search_code

Full per-tool breakdown → Model it in the token calculator →

WHAT CAN GO WRONG

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

RECOMMENDED RULES

Cap read operations

{
  "acp_list": {
    "limits": [
      {
        "counter": "acp_list_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

ALL 44 AVALANCHE AVAX MCP TOOLS

READ 44 tools

Read acp_list Read acp_lookup Read avalanche_docs_fetch Read avalanche_docs_list_sections Read avalanche_docs_search Read blockchain_get_contract_info Read blockchain_get_native_balance Read blockchain_lookup_address Read blockchain_lookup_chain Read blockchain_lookup_subnet Read blockchain_lookup_transaction Read blockchain_lookup_validator Read cli_lookup_command Read docs_fetch Read docs_list_sections Read docs_search Read github_get_file Read github_list_repositories Read github_search_code Read info_acps Read info_get_blockchain_id Read info_get_network_id Read info_get_network_name Read info_get_node_version Read info_get_tx_fee Read info_is_bootstrapped Read info_peers Read platform_get_balance Read platform_get_block Read platform_get_block_by_height Read platform_get_blockchains Read platform_get_current_supply Read platform_get_current_validators Read platform_get_height Read platform_get_min_stake Read platform_get_pending_validators Read platform_get_staking_asset_id Read platform_get_subnets Read platform_get_total_stake Read platform_get_tx Read platform_get_tx_status Read platform_get_utxos Read platform_get_validators_at Read rpc_lookup_method

FAQ

Is the Avalanche AVAX MCP server safe to use without restrictions? +

The Avalanche AVAX MCP server is primarily read-only with 44 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Avalanche AVAX MCP server expose? +

44 tools across 1 categories: Read. 44 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Avalanche AVAX MCP? +

Register the Avalanche AVAX 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 AVAX MCP tool call.

Deterministic rules across all 44 Avalanche AVAX MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE AVALANCHE AVAX MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

Avalanche AVAX MCP

// TOOL MAP

// CONTEXT-WINDOW COST

// WHAT CAN GO WRONG

// RECOMMENDED RULES

// ALL 44 AVALANCHE AVAX MCP TOOLS

// FAQ