get_judge
AI agents call get_judge to retrieve information from CourtListener MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite an empty tool description, the naming convention and context strongly suggest this retrieves judge profile information (aligning with the server's stated capability of 'judge profiles'). This is a read operation with no side effects. Confidence is slightly reduced due to the missing description, but the pattern across sibling tools and server purpose make misclassification unlikely.
From the tool's definition Tool name 'get_judge' and sibling tools like 'get_cluster', 'get_court', 'get_docket', 'get_educations', and 'get_opinion' all follow a 'get_*' pattern consistent with read-only retrieval operations.
Attacks that exploit this kind of access
get_judge. It is categorised as a Read tool in the CourtListener MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CourtListener MCP Server MCP server in PolicyLayer and add a rule for get_judge: 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 CourtListener MCP Server. Nothing to install.
get_judge 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_judge 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_judge. 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_judge is provided by the CourtListener MCP Server MCP server (upsd1/courtlistener-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 →