AI agents call get_court_filings to retrieve information from Legal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix strongly suggests this tool retrieves court filing documents from PACER without side effects. Although the description is empty, the naming convention and context of a legal research server that 'enables US case law search' and 'federal court filings through PACER' indicate this tool queries and returns court documents. PACER is a public system, so reading filings carries low risk.
From the tool's definition Tool name 'get_court_filings' uses the verb 'get', which indicates retrieval/read operations. The sibling tools on this server include 'get_case_details', 'get_case_record', 'get_federal_case', 'get_matter_details', 'get_matter_documents', and…
Attacks that exploit this kind of access
get_court_filings. It is categorised as a Read tool in the Legal MCP Server, which means it retrieves data without modifying state.
Register the Legal MCP server in PolicyLayer and add a rule for get_court_filings: 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 Legal. Nothing to install.
get_court_filings 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_court_filings 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_court_filings. 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_court_filings is provided by the Legal MCP server (jscottym/legal-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 →