AI agents call get_matter_documents 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.
This tool searches and retrieves documents from Clio (a practice management system) based on optional matter filtering. The verb 'search' and the absence of any language suggesting creation, modification, deletion, or execution indicates this is a read-only operation that queries existing data without changing state.
From the tool's definition Tool name 'get_matter_documents' and description 'Search documents in Clio, optionally filtered by matter' indicate a retrieval operation with no modifications or side effects.
Attacks that exploit this kind of access
Search documents in Clio, optionally filtered by matter. 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_matter_documents: 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_matter_documents 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_matter_documents 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_matter_documents. 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_matter_documents 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 →