get_judgment
AI agents call get_judgment 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 retrieves court judgment data from Taiwan's legal database. It performs a read-only query operation with no side effects on the underlying data. The blast radius of misuse is minimal—an AI agent could retrieve sensitive legal information but cannot modify, delete, or execute code through this tool.
From the tool's definition Tool name 'get_judgment' with sibling tools including 'search_judgments', 'get_citations', 'get_interpretation' indicate data retrieval operations.
Attacks that exploit this kind of access
get_judgment. 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 get_judgment: 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.
get_judgment 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 get_judgment 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 get_judgment. 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.
get_judgment 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 →