get_book
AI agents call get_book to retrieve information from Polymarket without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves order book data from Polymarket's CLOB without modification capability. The server's documented read-only nature and the pattern of get_* tools querying financial data without side effects classify this as a Read operation. No financial transactions, code execution, or data modification occurs—purely informational market data retrieval.
From the tool's definition Server explicitly described as 'read-only interface for querying markets, wallets, and order books.' Tool name 'get_book' aligns with read-only order book retrieval pattern seen in sibling tools (get_books, get_positions, get_prices, etc.).
Attacks that exploit this kind of access
get_book. It is categorised as a Read tool in the Polymarket MCP Server, which means it retrieves data without modifying state.
Register the Polymarket MCP server in PolicyLayer and add a rule for get_book: 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 Polymarket. Nothing to install.
get_book 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_book 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_book. 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_book is provided by the Polymarket MCP server (pr1m8/polymarket-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 →