Detect potentially redundant strategies based on correlation, tail dependence, and trading day overlap. Flags strategy pairs that may be adding risk without diversification benefit.
AI agents call strategy_similarity 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 strategy_similarity 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
Detect potentially redundant strategies based on correlation, tail dependence, and trading day overlap. Flags strategy pairs that may be adding risk without diversification benefit. 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 strategy_similarity: 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.
strategy_similarity 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 strategy_similarity 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 strategy_similarity. 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.
strategy_similarity 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.