Get real-time orderbook data for a specific instrument with bid/ask levels, depth, and spread.
AI agents call get_orderbook to retrieve information from Derive MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves real-time orderbook information (bid/ask levels, depth, spread) for a trading instrument. It is a pure read operation with no side effects—it does not execute trades, modify accounts, move funds, or delete data.
From the tool's definition Tool name 'get_orderbook' and description 'Get real-time orderbook data' indicate a retrieval operation that queries market data without modifying state or executing transactions.
Attacks that exploit this kind of access
Get real-time orderbook data for a specific instrument with bid/ask levels, depth, and spread. It is categorised as a Read tool in the Derive MCP MCP Server, which means it retrieves data without modifying state.
Register the Derive MCP server in PolicyLayer and add a rule for get_orderbook: 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 Derive MCP. Nothing to install.
get_orderbook is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_orderbook 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.
Set action: deny in the PolicyLayer policy for get_orderbook. 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.
get_orderbook is provided by the Derive MCP server (solenyaresearch0000/derive-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →