Browse Polymarket prediction markets. Filter by active/closed, order by volume/liquidity/endDate, page with limit/offset. Each market returns its question, outcomes + live outcome prices (implied probabilities), CLOB token ids (use with predict.price / predict.orderbook / predict.price-history), ...
AI agents call predict.markets to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries prediction market data from Polymarket with no side effects, no data modification, and no financial transactions. Despite existing in a server context involving financial settlement (2s.io pays per call in USDC), this specific tool is a read-only query interface that does not move money or commit financial obligations—it merely surfaces market information.
From the tool's definition Tool description explicitly states 'Read-only mirror of Polymarket' and lists read operations: 'Browse', 'Filter', 'order by', 'page with limit/offset'.
Attacks that exploit this kind of access
Browse Polymarket prediction markets. Filter by active/closed, order by volume/liquidity/endDate, page with limit/offset. Each market returns its question, outcomes + live outcome prices (implied probabilities), CLOB token ids (use with predict.price / predict.orderbook / predict.price-history), USD volume + liquidity, open/close dates, and the Polymarket URL. Read-only mirror of Polymarket\. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for predict.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 Mcp. Nothing to install.
predict.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 predict.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 predict.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.
predict.markets is provided by the MCP server (@2sio/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 →