AI agents use update_case to create or update resources in Mycase — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mycase environment.
The tool modifies existing case records (name, status, description, stage) but does not delete or irreversibly destroy data. Updates are reversible through subsequent edits. While this affects law firm operations and client data, the impact is contained to case metadata rather than financial transactions or destructive operations.
From the tool's definition Tool description explicitly states 'Update a case's name, status, description, or stage' — these are reversible modifications to case data.
Attacks that exploit this kind of access
Update a case's name, status, description, or stage. It is categorised as a Write tool in the Mycase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mycase MCP server in PolicyLayer and add a rule for update_case: 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.
update_case is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_case 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 update_case. 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.
update_case 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 →