Search questions at Council meetings
AI agents call search_questions to retrieve information from LegCo Search MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool's primary function is to search and retrieve parliamentary questions from Hong Kong Legislative Council meetings. This is a read-only operation that retrieves existing data without creating, modifying, deleting, or executing operations.
From the tool's definition search_questions retrieves and queries data about Council meeting questions without modifying or deleting any information. The description indicates pure search/query functionality with no side effects.
Attacks that exploit this kind of access
Search questions at Council meetings. It is categorised as a Read tool in the LegCo Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LegCo Search MCP Server MCP server in PolicyLayer and add a rule for search_questions: 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 LegCo Search MCP Server. Nothing to install.
search_questions 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_questions 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_questions. 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_questions is provided by the LegCo Search MCP Server MCP server (yellowcandle/legco-search-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 →