AI agents call get_class_definition_tool to retrieve information from Pharo Nc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns class definition information from the Pharo environment. It is a read-only operation with no side effects, no code execution, and no data modification. The blast radius of misuse is minimal—an agent could only learn structural information about classes already present in the system.
From the tool's definition Tool name 'get_class_definition_tool' and description 'Get the definition of a Pharo class' indicate a retrieval operation that queries class metadata without modification or execution.
Attacks that exploit this kind of access
Get the definition of a Pharo class. It is categorised as a Read tool in the Pharo Nc MCP Server, which means it retrieves data without modifying state.
Register the Pharo Nc MCP server in PolicyLayer and add a rule for get_class_definition_tool: 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 Pharo Nc. Nothing to install.
get_class_definition_tool 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_class_definition_tool 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_class_definition_tool. 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_class_definition_tool is provided by the Pharo Nc MCP server (mumez/pharo-nc-mcp-server). 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 →