search_judgments
AI agents call search_judgments to retrieve information from Mcp Taiwan Legal Db Integrated without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches court judgments in Taiwan's legal database, retrieving data without side effects. It is purely informational retrieval with no capacity to modify, delete, or execute external operations. The empty description reduces confidence slightly, but the semantic pattern of sibling tools and server design strongly indicate a read-only query function.
From the tool's definition Tool named 'search_judgments' with sibling tools following a consistent Read pattern (get_citations, get_interpretation, get_judgment, query_regulation, search_interpretations).
Attacks that exploit this kind of access
search_judgments. It is categorised as a Read tool in the Mcp Taiwan Legal Db Integrated MCP Server, which means it retrieves data without modifying state.
Register the Mcp Taiwan Legal Db Integrated MCP server in PolicyLayer and add a rule for search_judgments: 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 Mcp Taiwan Legal Db Integrated. Nothing to install.
search_judgments 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_judgments 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_judgments. 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_judgments is provided by the Mcp Taiwan Legal Db Integrated MCP server (oldbear-meme/mcp-taiwan-legal-db-integrated). 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 →