ClaudeSmalltalk

io.github.johnmci由 GitHub 账号 johnmci 发布v1.2.1更新于 Oct 24, 2026

MCP server for AI interaction with live Smalltalk images

发布方自己的服务:Claude Platform Docs

已验证STDIO仅桌面开发者工具AI 与机器学习

概览

AI 生成的概览

让助手通过委派的本地 LLM 浏览、求值并编辑运行中的 Squeak 或 Cuis Smalltalk 映像中的代码。

可以做什么
向 Claude Desktop 暴露一个工具 smalltalk_task,把 Smalltalk 任务委派给单独配置的 LLM。该代理拥有 14 个 VM 工具:求值表达式、浏览类、读取和写入方法源码、定义或删除类与方法、列出类与类别、遍历继承层次,以及保存映像。这些工具也可通过 st 命令行使用。
适用场景
当你希望助手检查或修改运行中的 Smalltalk 映像时使用,例如浏览类、求值表达式,或对 Squeak、Cuis 进行自主代码审查。适合已在 Smalltalk 环境中工作的开发者。
运行要求
在 macOS 桌面本地运行的进程,通过 uv 或 python3 启动,需要 Python 3.10+ 和 httpx(MQTT 还需 paho-mqtt)。需要 Squeak 6.0 或 Cuis 的 VM 与映像、包含 VM 路径的 smalltalk-mcp.json 配置,以及 LLM 提供方:本地 Ollama,或付费的 Anthropic、OpenAI、xAI 密钥。默认使用 TCP;MQTT 需要 broker。
安装前请注意
该代理可以定义和删除类与方法,并就地保存映像,因此改动会写入你的运行中映像。付费提供方会把 Smalltalk 源码发送到云端 API;只有 Ollama 配合 TCP 才保持本地。macOS TCC 会阻止 ~/Documents、~/Desktop 和 ~/Downloads,请把 VM 与映像文件放在 /Applications 或主目录。

安装

在 SourceWeft 中

  1. 打开 控制台中的 ClaudeSmalltalk,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

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:

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:

bash
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):

json
{  "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 use python3 as the command — but you'll need to install httpx yourself (pip install httpx or pip3 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)

ToolDescription
smalltalk_taskDelegate any Smalltalk task to a locally-configured LLM. No source code leaves your machine.

VM Tools (14, available to the agent)

ToolDescription
smalltalk_evaluateExecute Smalltalk code and return result
smalltalk_browseGet class metadata (superclass, ivars, methods)
smalltalk_method_sourceView source code of a method
smalltalk_define_classCreate or modify a class definition
smalltalk_define_methodAdd or update a method
smalltalk_delete_methodRemove a method from a class
smalltalk_delete_classRemove a class from the system
smalltalk_list_classesList classes matching a prefix
smalltalk_hierarchyGet superclass chain
smalltalk_subclassesGet immediate subclasses
smalltalk_list_categoriesList all system categories
smalltalk_classes_in_categoryList classes in a category
smalltalk_save_imageSave the current image in place
smalltalk_save_as_new_versionSave 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

ProviderAPICostConfig key
Ollama/v1/chat/completionsFree (local)"provider": "ollama"
Anthropic/v1/messages (httpx)Paid"provider": "anthropic"
OpenAI/v1/chat/completionsPaid"provider": "openai"
xAI/v1/chat/completionsPaid"provider": "xai"

All providers use httpx (included as a dependency) — no additional packages to install.

Transport Options

TransportHowUse Case
tcpToken-authenticated TCP to Squeak VMRecommended — VM is its own server
mqttMQTT broker to remote imageRemote 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

OptionArchitectureGuide
OpenClawTelegram/Discord ↔ OpenClaw ↔ SqueakOPENCLAW-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

FileDescription
Claude.SmalltalkInterface.mcpbDesktop extension — double-click to install
CLAUDE-README-MCPB.mdSetup guide bundled with the extension
smalltalk_agent_mcp.pyMCP server (stdio JSON-RPC for Claude Desktop)
smalltalk_agent.pyAgent with tool-calling loop, TcpBridge + MqttBridge
openclaw/smalltalk.pyst CLI — direct TCP access to all 14 tools
openclaw/mqtt_bridge.pyMQTT CLI bridge for Cuis/remote images
smalltalk-mcp-example.jsonStarter config — copy and edit
SKILL.mdDrag into Claude Desktop for Smalltalk best practices
MCP-Server-Squeak.stMCP server fileIn for Squeak 6.0 (TCP transport)
MCP-Server.pck.stMCP server package for Cuis
examples/Config examples for all providers and transports

License

MIT License — see LICENSE

来源:README.md,提交 e7bea13

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.2.1最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Claude 集成