AI agents call get_document_data to retrieve information from Mycase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves document data or URLs without creating, modifying, deleting, or executing anything. It has no side effects and fits the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' The low severity reflects that accessing document data in a law firm context poses minimal risk if misused—at worst, it results in information disclosure of documents the AI might…
From the tool's definition Tool name and description state 'Get the download URL or data' with no modification, deletion, or execution capability. The verb 'get' and focus on retrieval indicates read-only access.
Attacks that exploit this kind of access
Get the download URL or data for a document's latest version. It is categorised as a Read tool in the Mycase MCP Server, which means it retrieves data without modifying state.
Register the Mycase MCP server in PolicyLayer and add a rule for get_document_data: 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 Mycase. Nothing to install.
get_document_data 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_document_data 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_document_data. 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_document_data is provided by the Mycase MCP server (rosenadvertising/mycase-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 →