AI agents call search_classes_like to retrieve information from Pharo Smalltalk Interop without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search and query operations that retrieve class information from a Pharo image without modifying state are Read category tools. The absence of verbs like 'set', 'apply', 'delete', 'execute', or 'modify' in the tool name, combined with the context of sibling read-only tools, indicates this performs a retrieval operation with no side effects.
From the tool's definition Tool name 'search_classes_like' indicates a search/query operation. The description is empty, but the naming convention and position among sibling tools (which include various read operations like get_class_comment, get_class_source, get_method_source)…
Documented attack patterns abuse exactly the kind of access search_classes_like gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pharo Smalltalk Interop, and nothing reaches the server without passing your rules. This is the rule we recommend for search_classes_like:
{
"version": "1",
"default": "deny",
"tools": {
"search_classes_like": {}
}
}search_classes_like is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
search_classes_like. It is categorised as a Read tool in the Pharo Smalltalk Interop MCP Server, which means it retrieves data without modifying state.
Register the Pharo Smalltalk Interop MCP server in PolicyLayer and add a rule for search_classes_like: 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 Smalltalk Interop. Nothing to install.
search_classes_like 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 search_classes_like 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 search_classes_like. 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.
search_classes_like is provided by the Pharo Smalltalk Interop MCP server (mumez/pharo-smalltalk-interop-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pharo Smalltalk Interop, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
23 Pharo Smalltalk Interop tools catalogued and risk-classified — across an index of 43,000+ MCP servers.