AI agents call get_top_markets to retrieve information from Lpxpoly without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns market data without creating, modifying, deleting, or executing anything. It is a straightforward read operation returning current market information. While the server involves financial markets and payments, this specific tool only retrieves public market data, not financial transactions.
From the tool's definition Tool retrieves 'most active Polymarket markets by volume with current probabilities' — a data retrieval operation with no state modifications or side effects.
Attacks that exploit this kind of access
Get the most active Polymarket markets by volume with current probabilities. It is categorised as a Read tool in the Lpxpoly MCP Server, which means it retrieves data without modifying state.
Register the Lpxpoly MCP server in PolicyLayer and add a rule for get_top_markets: 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 Lpxpoly. Nothing to install.
get_top_markets 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_top_markets 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_top_markets. 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_top_markets is provided by the Lpxpoly MCP server (unixlamadev-spec/lpxpoly-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 →