AI agents call list_case_roles 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 queries and returns existing case role definitions (e.g., plaintiff, defendant, attorney) without creating, modifying, or deleting data. It is a straightforward read operation with minimal risk, as it only exposes metadata about role types rather than sensitive case or client information. The blast radius of misuse is minimal since listing available roles cannot cause harm.
From the tool's definition Tool name 'list_case_roles' and description 'List all case roles' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all case roles (e.g. plaintiff, defendant, attorney). 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 list_case_roles: 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.
list_case_roles 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 list_case_roles 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 list_case_roles. 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.
list_case_roles 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 →