AI agents invoke run_class_test to trigger actions in Pharo Smalltalk Interop. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Running tests in a live Pharo image can trigger side effects (code modification, data changes, external calls) depending on what those tests do. This is Execute rather than Read because tests are not merely queries—they actively run code and may have consequences beyond retrieving information.
From the tool's definition Tool name is 'run_class_test' which indicates execution of test code in a Pharo Smalltalk image. The sibling tools include 'eval' and 'eval_code', establishing this server's pattern of executing arbitrary code.
Documented attack patterns abuse exactly the kind of access run_class_test 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 run_class_test:
{
"version": "1",
"default": "deny",
"tools": {
"run_class_test": {
"limits": [
{
"counter": "run_class_test_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_class_test stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
run_class_test. It is categorised as a Execute tool in the Pharo Smalltalk Interop MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pharo Smalltalk Interop MCP server in PolicyLayer and add a rule for run_class_test: 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.
run_class_test is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_class_test 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 run_class_test. 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.
run_class_test 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.