search_nars_reports
AI agents call search_nars_reports to retrieve information from Open Assembly without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to search or retrieve legislative reports from the Korean National Assembly's database. While the description is empty, the context of the MCP server (querying bills, members, votes, committees) and the consistent naming pattern across sibling Read tools strongly suggest this performs data retrieval without side effects. No destructive, financial, or execution-based operations are indicated.
From the tool's definition Tool name 'search_nars_reports' indicates a search/query operation against the National Assembly Records System (NARS).
Attacks that exploit this kind of access
search_nars_reports. It is categorised as a Read tool in the Open Assembly MCP Server, which means it retrieves data without modifying state.
Register the Open Assembly MCP server in PolicyLayer and add a rule for search_nars_reports: 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 Open Assembly. Nothing to install.
search_nars_reports 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_nars_reports 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_nars_reports. 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_nars_reports is provided by the Open Assembly MCP server (kyusik-yang/open-assembly-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 →