Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
CorporateSmalltalkConsultingLtd avatar

ClaudeSmalltalk

  • 18 repo stars
  • Updated July 14, 2026
  • CorporateSmalltalkConsultingLtd/ClaudeSmalltalk

ClaudeSmalltalk is a MCP server that lets AI agents interact with live Smalltalk images over stdio.

About

ClaudeSmalltalk is a Model Context Protocol server that connects AI coding agents to running Smalltalk images so conversation can turn into live exploration, not static text dumps. developers and consultants who still ship or maintain Smalltalk stacks—or who learn through live systems—get a stdio transport server published on PyPI as claude-smalltalk. You register the MCP entry in Claude Code, Cursor, or another MCP-capable client, point it at your image, and the agent can interact with the live environment through the protocol instead of guessing from screenshots or pasted code. The footprint is narrow compared to mainstream web stacks, but for that niche it closes the gap between agent reasoning and a real REPL-style loop. Treat it as agent tooling: install Python dependencies, configure the server, and keep your Smalltalk image running locally or on a reachable host.

  • Stdio MCP server (PyPI package claude-smalltalk v1.2.1) for live Smalltalk images
  • Bridges Claude and compatible agents to an interactive Smalltalk runtime
  • Self-hosted GitHub repo CorporateSmalltalkConsultingLtd/ClaudeSmalltalk
  • Targets builders maintaining or experimenting with Smalltalk systems alongside AI assistants

ClaudeSmalltalk by the numbers

  • Data as of Jul 15, 2026 (Skillselion catalog sync)
terminal
claude mcp add claude-smalltalk -- uvx claude-smalltalk

Add your badge

Show developers this MCP server is listed on Skillselion. Paste this into your README.

Listed on Skillselion
repo stars18
Packageclaude-smalltalk
TransportSTDIO
AuthNone
Last updatedJuly 14, 2026
RepositoryCorporateSmalltalkConsultingLtd/ClaudeSmalltalk

What it does

Let your coding agent inspect, evaluate, and drive a live Smalltalk image instead of copy-pasting snippets back and forth.

Who is it for?

maintainers, consultants, or learners who already run Smalltalk and want Claude or Cursor wired into that image.

Skip if: Skip if you're building only TypeScript or Python SaaS with no Smalltalk runtime or appetite for niche language tooling.

What you get

After you register the MCP server, your agent can work against the live image through structured tool calls instead of one-off paste workflows.

  • Registered stdio MCP server in your agent config
  • Agent-accessible tools against your live Smalltalk image

By the numbers

  • Server version 1.2.1 on PyPI identifier claude-smalltalk
  • Transport type stdio per MCP server schema
  • Repository: github.com/CorporateSmalltalkConsultingLtd/ClaudeSmalltalk
README.md

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:

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 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)

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

Recommended MCP Servers

How it compares

MCP runtime bridge for Smalltalk, not a general web-automation or database MCP.

FAQ

Who is ClaudeSmalltalk for?

It is for developers and consultants who work with live Smalltalk images and want MCP-capable agents to participate in that session.

When should I use ClaudeSmalltalk?

Use it during build and integration work when you need an agent to query or steer a running Smalltalk environment rather than edit files in isolation.

How do I add ClaudeSmalltalk to my agent?

Install the PyPI package claude-smalltalk (v1.2.1), configure stdio MCP in Claude Code or Cursor per your client docs, and ensure your Smalltalk image is reachable to the server process.

Developer Toolsintegrations

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.