Get recent trades for a market.
AI agents call get_market_trades to retrieve information from Question Market without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical trade data from a prediction market without creating, modifying, deleting, or executing any operations. It is a straightforward query operation with no side effects, fitting the Read category. The low severity reflects that accessing publicly available market history poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_market_trades' and description 'Get recent trades for a market' indicate data retrieval with no modification or execution of external operations.
Attacks that exploit this kind of access
Get recent trades for a market. It is categorised as a Read tool in the Question Market MCP Server, which means it retrieves data without modifying state.
Register the Question Market MCP server in PolicyLayer and add a rule for get_market_trades: 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 Question Market. Nothing to install.
get_market_trades 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_market_trades 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_market_trades. 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_market_trades is provided by the Question Market MCP server (qmrkt/mcp-server). 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 →