AI agents invoke eval 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.
The tool name 'eval' on a server designed to communicate with a local Pharo Smalltalk image almost certainly executes arbitrary Smalltalk code. The sibling tool 'eval_code' confirms this pattern. Arbitrary code execution in a live Smalltalk image can have wide blast radius including file system access, network calls, and system modification. Confidence is slightly reduced due to empty description.
From the tool's definition Tool name 'eval' on a Pharo Smalltalk interop server with sibling tool 'eval_code' strongly implies arbitrary code evaluation in a Smalltalk image
Documented attack patterns abuse exactly the kind of access eval 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 eval:
{
"version": "1",
"default": "deny",
"tools": {
"eval": {
"limits": [
{
"counter": "eval_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}eval 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.
eval. 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 eval: 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.
eval 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 eval 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 eval. 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.
eval 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.