# ClaudeSmalltalk

> Use this tool when you need to interact with live Smalltalk environments, such as Cuis and Squeak, to evaluate code, browse metadata, and manage classes and methods. It solves problems related to integrating AI with Smalltalk platforms, providing a range of deployment options and tools for seamless interaction. With inputs including code snippets and method calls, and outputs like evaluation results and class definitions, use ClaudeSmalltalk in contexts where dynamic Smalltalk environment interaction is required.

Canonical page: https://skillsregistry.net/skills/claudesmalltalk  
JSON: https://api.skillsregistry.net/v1/skills/claudesmalltalk

## Description

Enables AI interaction with live Smalltalk environments through the Model Context Protocol, supporting both Cuis and Squeak platforms. Offers multiple deployment options including native stdio-based MCP servers for Cuis and Squeak, a Python/MQTT bridge for asynchronous messaging, and integrations with OpenAI and Clawdbot. Provides 14 tools covering code evaluation, class metadata browsing, method source viewing, class and method definition, deletion operations, class hierarchy inspection, and category management. Features non-blocking I/O to keep the Smalltalk GUI responsive during MCP operations, dev mode with persistent saving, and headless operation support via Xvfb on Linux.

## Trust

- **Trust score (0–1):** 0.57
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/claudesmalltalk)
- **Repository:** <https://github.com/corporatesmalltalkconsultingltd/claudesmalltalk>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "claudesmalltalk"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/claudesmalltalk` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/claudesmalltalk/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt