Find classes/blocks by name, pattern, or package
AI agents call find_classes to retrieve information from XMI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval and searching within an XMI model structure. It has no side effects—it does not modify, delete, execute, or move any data. It follows the 'Read' pattern of searching and retrieving information from an existing data structure. The low severity reflects minimal blast radius even if misused by an AI agent, as it can only expose existing model information.
From the tool's definition Tool name 'find_classes' and description 'Find classes/blocks by name, pattern, or package' indicate a search/query operation that retrieves data without modification or execution.
Attacks that exploit this kind of access
Find classes/blocks by name, pattern, or package. It is categorised as a Read tool in the XMI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the XMI MCP Server MCP server in PolicyLayer and add a rule for find_classes: 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 XMI MCP Server. Nothing to install.
find_classes 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 find_classes 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 find_classes. 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.
find_classes is provided by the XMI MCP Server MCP server (mriiot/xmimcp). 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 →