// SCAN REPORT

Derive MCP

31 tools. 6 can modify or destroy data without limits.

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

Last updated: 4 Jul 2026

6 can modify or destroy data

25 read-only

31 tools total

Community server · catalogue entry verified 04/07/2026

How to control Derive MCP ↓

TOOL MAP

What Derive MCP exposes to your agents

Read (25) Write / Execute (2) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Derive MCP tools

Financial · Critical execute_quote Executing a quoted trade directly commits financial obligations and moves assets/positions. Financial · Critical place_order Placing orders in financial markets commits funds and creates binding trade obligations. Destructive · High cancel_all_orders Cancelling all open orders is an irreversible action — once orders are cancelled in a trading context, the market positions/queue priority cannot be restored. Destructive · High cancel_order Cancelling an order is an irreversible action — once cancelled, the order is gone and cannot be reinstated.

6 of Derive MCP's 31 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Derive MCP

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

Block financial tools by default

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

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

Deny destructive operations

{
  "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

{
  "send_rfq": {
    "limits": [
      {
        "counter": "send_rfq_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_account": {
    "limits": [
      {
        "counter": "get_account_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 Derive 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 DERIVE →

Instant setup, no code required.

FULL CATALOGUE

All 31 Derive MCP tools

FINANCIAL 2 tools

Financial execute_quote Execute a quoted trade at the quoted price. Requires authentication. Financial place_order Place a new order (limit or market). Requires authentication and private key for signing.

DESTRUCTIVE 2 tools

Destructive cancel_all_orders Cancel all open orders for a subaccount. Optionally filter by currency or instrument. Requires authentication. Destructive cancel_order Cancel an open order by order ID. Requires authentication.

EXECUTE 1 tools

Execute replace_order Replace an existing order (cancel old and place new) in one atomic operation. Requires authentication.

WRITE 1 tools

Write send_rfq Send a Request For Quote to get custom pricing from market makers. Requires authentication.

READ 25 tools

EXPLORE

Related servers

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

FAQ

Questions about Derive MCP

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

Yes. The Derive MCP server exposes 2 financial tools including execute_quote, place_order. 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 Derive MCP server? +

Yes. The Derive MCP server exposes 2 destructive tools including cancel_all_orders, cancel_order. 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 Derive MCP? +

The Derive MCP server has 1 write tools including send_rfq. 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 Derive MCP.

How many tools does the Derive MCP server expose? +

31 tools across 4 categories: Destructive, Execute, Read, Write. 25 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Derive MCP? +

Register the Derive 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 Derive MCP tool call.

Deterministic rules across all 31 Derive MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DERIVE →

Instant setup, no code required.

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