Search for specific stock information by code or name
AI agents call searchStock to retrieve information from TWSE MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves stock information without creating, modifying, executing operations, or deleting data. It is a straightforward search/lookup operation that reads publicly available market data from the Taiwan Stock Exchange. The lack of side effects and purely informational purpose places it clearly in the Read category with low severity.
From the tool's definition Tool name 'searchStock' and description 'Search for specific stock information by code or name' indicate data retrieval with no modification or execution capability.
Attacks that exploit this kind of access
Search for specific stock information by code or name. It is categorised as a Read tool in the TWSE MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TWSE MCP Server MCP server in PolicyLayer and add a rule for searchStock: 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 TWSE MCP Server. Nothing to install.
searchStock 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 searchStock 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 searchStock. 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.
searchStock is provided by the TWSE MCP Server MCP server (pyang2045/twsemcp). 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 →