find_authorities_cited
AI agents call find_authorities_cited 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 the empty description, the tool name and the pattern of sibling tools (all retrieval-focused: get_opinion, get_docket, get_judge, get_court, analyze_citation_network, find_citing_opinions) indicate this is a read-only query tool that retrieves citations or authorities referenced in legal documents. There are no indications of side effects, data modification, code execution, or destructive operations.
From the tool's definition Tool name 'find_authorities_cited' and sibling tools like 'analyze_citation_network' and 'find_citing_opinions' all indicate retrieval and analysis of legal citations and references.
Attacks that exploit this kind of access
find_authorities_cited. 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 find_authorities_cited: 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.
find_authorities_cited 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 find_authorities_cited 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 find_authorities_cited. 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.
find_authorities_cited 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 →