io.github.johnmci/ClaudeSmalltalk
编码与调试by corporatesmalltalkconsultingltd
MCP server for AI interaction with live Smalltalk images
什么是 io.github.johnmci/ClaudeSmalltalk?
MCP server for AI interaction with live Smalltalk images
README
ClaudeSmalltalk
Connect Claude Desktop to a live Smalltalk programming environment. Browse classes, evaluate expressions, define methods, and run autonomous code review — all against a running Squeak or Cuis image.
Developed by John M McIntosh, Corporate Smalltalk Consulting Ltd. 2026
What It Does
The Squeak VM provides 14 MCP tools — evaluate code, browse classes, read/write methods, navigate hierarchies, and save the image. Claude Desktop accesses them via smalltalk_task, which delegates all Smalltalk interaction to a locally-configured LLM (Ollama for free/local, or Anthropic/OpenAI/xAI) — no source code leaves your machine.
You → Claude Desktop → smalltalk_task → Your LLM → Live Smalltalk Image (TCP)
(MCP server) (Ollama) (Squeak or Cuis)
The agent isolates Smalltalk reasoning from your chat model. Claude Desktop triggers the work, but a separate model (which can be local and free) does the actual Smalltalk coding.
Quick Start
1. Get a Smalltalk VM and Image
Squeak (recommended):
- Download Squeak 6.0 — the All-in-One package includes VM and image
- Follow SQUEAK-SETUP.md to install the MCP server into the image
Cuis Smalltalk:
- Clone Cuis-Smalltalk-Dev
- Follow CUIS-SETUP.md to build a ClaudeCuis image
macOS note: Place the VM and image files in
/Applications/or your home directory. Files in~/Documents/or~/Desktop/may be blocked by macOS privacy restrictions (TCC). See macOS Permissions below.
2. Create a Configuration File and Install
Follow CLAUDE-README-MCPB.md — it covers creating your smalltalk-mcp.json config and installing the desktop extension.
Copy a starter config from examples/ and set your VM paths:
cp examples/smalltalk-mcp-ollama.json smalltalk-mcp.json
# Edit vm.binary and vm.image to match your install
The VM auto-starts on first use — no manual launch needed. Token auth is handled automatically.
See examples/ for Anthropic, OpenAI, xAI, and MQTT variants.
3. Configure Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"smalltalkAgent": {
"command": "uv",
"args": ["run", "/path/to/ClaudeSmalltalk/smalltalk_agent_mcp.py"],
"env": {
"SMALLTALK_MCP_CONFIG": "/path/to/smalltalk-mcp.json"
}
}
}
}
Requires Python 3.10+. Dependencies (httpx) are resolved automatically by uv. Install uv if you don't have it by following the official installation instructions there (for example via your package manager where available). If you choose to use an install script, review it first and follow any checksum or signature verification steps described in the uv documentation.
Alternatively, if you prefer not to use
uv, you can usepython3as the command — but you'll need to installhttpxyourself (pip install httpxorpip3 install httpx). For MQTT transport, also:pip install paho-mqtt.
4. Verify It Works
Open Claude Desktop and ask:
"List all Smalltalk classes that start with String"
Available Tools
Claude Desktop (1 tool)
| Tool | Description |
|---|---|
smalltalk_task | Delegate any Smalltalk task to a locally-configured LLM. No source code leaves your machine. |
VM Tools (14, available to the agent)
| Tool | Description |
|---|---|
smalltalk_evaluate | Execute Smalltalk code and return result |
smalltalk_browse | Get class metadata (superclass, ivars, methods) |
smalltalk_method_source | View source code of a method |
smalltalk_define_class | Create or modify a class definition |
smalltalk_define_method | Add or update a method |
smalltalk_delete_method | Remove a method from a class |
smalltalk_delete_class | Remove a class from the system |
smalltalk_list_classes | List classes matching a prefix |
smalltalk_hierarchy | Get superclass chain |
smalltalk_subclasses | Get immediate subclasses |
smalltalk_list_categories | List all system categories |
smalltalk_classes_in_category | List classes in a category |
smalltalk_save_image | Save the current image in place |
smalltalk_save_as_new_version | Save image/changes as next version number |
All 14 tools are also available directly via the st CLI (openclaw/smalltalk.py).
Configuration Reference
Supported LLM Providers
| Provider | API | Cost | Config key |
|---|---|---|---|
| Ollama | /v1/chat/completions | Free (local) | "provider": "ollama" |
| Anthropic | /v1/messages (httpx) | Paid | "provider": "anthropic" |
| OpenAI | /v1/chat/completions | Paid | "provider": "openai" |
| xAI | /v1/chat/completions | Paid | "provider": "xai" |
All providers use httpx (included as a dependency) — no additional packages to install.
Transport Options
| Transport | How | Use Case |
|---|---|---|
tcp | Token-authenticated TCP to Squeak VM | Recommended — VM is its own server |
mqtt | MQTT broker to remote image | Remote images, Cuis with MQTT handler |
tcp is the default. The Squeak VM runs MCPTcpTransport and listens on a local port. The agent auto-starts the VM on first use, generates a UUID token, and connects per-request with JSON-RPC + token auth.
mqtt connects through an MQTT broker. Used for remote images or Cuis with the MQTT LLM handler.
macOS Permissions
macOS Transparency, Consent, and Control (TCC) restricts which directories applications can access.
Safe locations (no extra permissions needed):
/Applications/— recommended for VM and image files~/(home directory root) — works for config files
Restricted locations (will cause errors):
~/Documents/,~/Desktop/,~/Downloads/
Other Integration Options
| Option | Architecture | Guide |
|---|---|---|
| OpenClaw | Telegram/Discord ↔ OpenClaw ↔ Squeak | OPENCLAW-SETUP.md |
Security
The extension only connects to a local Smalltalk image over TCP (localhost only). No source code is sent to cloud APIs when using Ollama.
With Ollama + TCP transport, no Smalltalk source code leaves your machine.
Dual security audit details: SECURITY.md
Files
| File | Description |
|---|---|
Claude.SmalltalkInterface.mcpb | Desktop extension — double-click to install |
CLAUDE-README-MCPB.md | Setup guide bundled with the extension |
smalltalk_agent_mcp.py | MCP server (stdio JSON-RPC for Claude Desktop) |
smalltalk_agent.py | Agent with tool-calling loop, TcpBridge + MqttBridge |
openclaw/smalltalk.py | st CLI — direct TCP access to all 14 tools |
openclaw/mqtt_bridge.py | MQTT CLI bridge for Cuis/remote images |
smalltalk-mcp-example.json | Starter config — copy and edit |
SKILL.md | Drag into Claude Desktop for Smalltalk best practices |
MCP-Server-Squeak.st | MCP server fileIn for Squeak 6.0 (TCP transport) |
MCP-Server.pck.st | MCP server package for Cuis |
examples/ | Config examples for all providers and transports |
License
MIT License — see LICENSE
常见问题
io.github.johnmci/ClaudeSmalltalk 是什么?
MCP server for AI interaction with live Smalltalk images
相关 Skills
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。