Search bills from LegCo database
AI agents call search_bills 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.
This tool performs data retrieval from a public legislative database. It has no side effects—it queries existing bills without creating, modifying, deleting, or executing any operations. The function is purely informational, comparable to searching public records. Blast radius is minimal as misuse would only result in unauthorized information access to publicly-intended legislative data.
From the tool's definition The tool name is 'search_bills' and description states it 'Search bills from LegCo database'. This is a query operation that retrieves legislative data without modifying, deleting, or executing code.
Attacks that exploit this kind of access
Search bills from LegCo database. 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_bills: 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_bills 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_bills 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_bills. 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_bills 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 →