st-eval

Execute Smalltalk Code

Evaluate arbitrary Smalltalk expressions in the running Smalltalk image via mcp__smalltalk-interop__eval.

Essential Rules

Always use printString — MCP returns serialized output. Raw objects cause errors or unreadable results:

✅ MyClass new doSomething printString
✅ collection printString
❌ MyClass new doSomething

Wrap risky code in on:do: — Uncaught errors in eval crash the MCP call with no useful message:

| result |
result := Array new: 2.
[ result at: 1 put: (riskyOperation) printString ]
  on: Error do: [:ex | result at: 2 put: ex description].
^ result

Use fork for blocking operations — Code that opens a dialog or blocks the image will cause the MCP call to hang indefinitely. Detach it:

[ <blocking expression> ] fork.
^ 'started'

Common Patterns

Connection check

Smalltalk version

Inspect intermediate values

| step1 step2 |
step1 := objA computeStep1.
step2 := step1 processStep2.
^ { 'step1' -> step1 printString. 'step2' -> step2 printString } asDictionary printString

Inspect object state

{
  'class' -> obj class name.
  'value' -> obj printString.
  'size'  -> obj size printString
} asDictionary printString

Safe collection access

collection ifEmpty: ['empty'] ifNotEmpty: [:col | col first printString]

Error-capturing eval

| result |
result := Array new: 2.
[
  | obj |
  obj := MyClass new name: 'Test'.
  result at: 1 put: obj process printString.
] on: Error do: [:ex |
  result at: 2 put: ex description
].
^ result

Troubleshooting

Symptom	Cause	Fix
MCP call hangs / no response	Blocking operation (dialog, modal, infinite loop)	Wrap in fork
Error: cannot serialize	Returning raw object	Add printString
Debugger window opened in the Smalltalk image	Uncaught error triggered the debugger	Close debugger in the Smalltalk image, then re-eval with on:do:
MessageNotUnderstood	Method doesn't exist or typo	Check with mcp__smalltalk-interop__search_implementors