Search for trading contracts
AI agents call search_contracts to retrieve information from Shioaji MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation to retrieve contract data from the trading system. It has no side effects on accounts, positions, or orders. While it is part of a financial trading system, the tool itself only retrieves information (fitting the Read category). The severity is low because misuse would only expose market data without financial impact.
From the tool's definition Tool name 'search_contracts' and description 'Search for trading contracts' indicate a query operation that retrieves contract information without modifying state or triggering trades.
Attacks that exploit this kind of access
Search for trading contracts. It is categorised as a Read tool in the Shioaji MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Shioaji MCP Server MCP server in PolicyLayer and add a rule for search_contracts: 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 Shioaji MCP Server. Nothing to install.
search_contracts 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 search_contracts 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 search_contracts. 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.
search_contracts is provided by the Shioaji MCP Server MCP server (offbeat-studio/shioaji-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 →