Replay a trade using historical minute-level option bars. Reads option-leg quotes via QuoteStore and underlying bars via SpotStore (cache only); missing data yields a degenerate replay. Use the data-pipeline tools to backfill cache. Returns minute-by-minute P&L path with MFE (Maximum Favorable Ex...
AI agents call replay_trade to retrieve information from Tradeblocks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though replay_trade only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Replay a trade using historical minute-level option bars. Reads option-leg quotes via QuoteStore and underlying bars via SpotStore (cache only); missing data yields a degenerate replay. Use the data-pipeline tools to backfill cache. Returns minute-by-minute P&L path with MFE (Maximum Favorable Excursion) and MAE (Maximum Adverse Excursion). Two modes: (A) Hypothetical \u2014 provide explicit legs with strikes, expiry, entry prices. (B) Tradelog \u2014 provide block_id + trade_index to replay an existing trade from your data. It is categorised as a Read tool in the Tradeblocks MCP Server, which means it retrieves data without modifying state.
Register the Tradeblocks MCP server in PolicyLayer and add a rule for replay_trade: 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 Tradeblocks. Nothing to install.
replay_trade 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 replay_trade 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 replay_trade. 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.
replay_trade is provided by the Tradeblocks MCP server (tradeblocks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.