// SCAN REPORT

Aevo-MCP

34 tools. 9 can modify or destroy data without limits.

8 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

9 can modify or destroy data

25 read-only

34 tools total

Community server · catalogue entry verified 03/07/2026

How to control Aevo-MCP ↓

TOOL MAP

What Aevo-MCP exposes to your agents

Read (25) Write / Execute (1) Destructive / Financial (8)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Aevo-MCP tools

Financial · Critical aevo_build_order Although the description is empty, the tool name 'aevo_build_order' on a financial trading platform (Aevo) strongly suggests it constructs or prepares a trade order. Financial · Critical aevo_create_order Creating an order on a financial trading platform directly commits a financial obligation or initiates a trade. Financial · Critical aevo_register_account While the description is empty, the tool name 'aevo_register_account' on a financial trading platform strongly implies account registration/creation, which could establish financial obligations or enable trading activity Financial · High aevo_update_leverage Updating leverage on a trading platform directly affects the risk profile and potential financial exposure of trading positions.

9 of Aevo-MCP's 34 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Aevo-MCP

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

Block financial tools by default

{
  "aevo_build_order": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations

{
  "aevo_cancel_all_orders": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "aevo_clear_auth": {
    "limits": [
      {
        "counter": "aevo_clear_auth_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "aevo_authenticate": {
    "limits": [
      {
        "counter": "aevo_authenticate_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 Aevo-MCP — 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 AEVO-MCP →

Instant setup, no code required.

FULL CATALOGUE

All 34 Aevo-MCP tools

FINANCIAL 5 tools

Financial aevo_build_order aevo_build_order Financial aevo_create_order aevo_create_order Financial aevo_onboard aevo_onboard Financial aevo_register_account aevo_register_account Financial aevo_update_leverage aevo_update_leverage

DESTRUCTIVE 3 tools

Destructive aevo_cancel_all_orders aevo_cancel_all_orders Destructive aevo_cancel_order Cancel a single order by order_id. Destructive aevo_cancel_orders Cancel multiple orders in one request.

WRITE 1 tools

Write aevo_clear_auth Clear credentials for the current MCP client session.

READ 25 tools

Read aevo_authenticate aevo_authenticate Read aevo_get_account aevo_get_account Read aevo_get_expiries Return available expiry dates for an asset's options/futures. Read aevo_get_funding_history aevo_get_funding_history Read aevo_get_funding_rate Return the current funding rate for a perpetual instrument. Read aevo_get_index_history aevo_get_index_history Read aevo_get_index_price Return the index (spot reference) price for an asset. Read aevo_get_instrument Return full instrument metadata by name or id. Read aevo_get_mark_history aevo_get_mark_history Read aevo_get_order aevo_get_order Read aevo_get_order_history aevo_get_order_history Read aevo_get_orderbook Return top 10 bids and asks for a given instrument. Read aevo_get_portfolio Return portfolio summary: balance, pnl, unrealized_pnl, greeks. Read aevo_get_positions aevo_get_positions Read aevo_get_server_time Return the AEVO exchange server time. Read aevo_get_settlement_history Return settlement history, optionally filtered by asset. Read aevo_get_statistics Return exchange-wide market statistics including volume and open interest. Read aevo_get_status Return MCP runtime and AEVO identity context. Read aevo_get_trade_fills aevo_get_trade_fills Read aevo_get_trade_history Return recent public trades for an instrument. Read aevo_healthcheck Verify connectivity to the AEVO API by fetching market data. Read aevo_list_assets List all supported assets on AEVO exchange. Read aevo_list_markets aevo_list_markets Read aevo_list_orders aevo_list_orders Read aevo_ping Check that the AEVO MCP server is running and responsive.

EXPLORE

Related servers

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

FAQ

Questions about Aevo-MCP

Can an AI agent move money through the Aevo- MCP server? +

Yes. The Aevo-MCP server exposes 5 financial tools including aevo_build_order, aevo_create_order, aevo_onboard. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

Can an AI agent delete data through the Aevo- MCP server? +

Yes. The Aevo-MCP server exposes 3 destructive tools including aevo_cancel_all_orders, aevo_cancel_order, aevo_cancel_orders. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Aevo-MCP? +

The Aevo-MCP server has 1 write tools including aevo_clear_auth. 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 Aevo-MCP.

How many tools does the Aevo- MCP server expose? +

34 tools across 4 categories: Destructive, Execute, Read, Write. 25 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on Aevo-MCP? +

Register the Aevo- 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 Aevo-MCP tool call.

Deterministic rules across all 34 Aevo-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AEVO-MCP →

Instant setup, no code required.

34 Aevo-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.