AIBase
EN
Explore
Claudesmalltalk
C

Claudesmalltalk

ClaudeSmalltalk is a project that connects Claude Desktop to a running Smalltalk programming environment. It provides 14 tools such as code evaluation, class browsing, and method definition through the MCP protocol, supports local or cloud LLM drivers, and ensures that the code is secure and does not leave the local machine.
Developer toolsEducation and learning tools#Smalltalk development#MCP tool#Local AI#Code security.Python
2.5 points
3.9K
Open Site

Overview

Installation

Content Details

Alternatives

What is ClaudeSmalltalk?

ClaudeSmalltalk is a Model Context Protocol (MCP) server that acts as a bridge between Claude Desktop and the Smalltalk programming environment. It allows you to have conversations with Claude in natural language, and Claude can operate your Smalltalk development environment in real-time, execute code, browse class structures, modify methods, etc. The system uses a dual architecture: Claude Desktop handles conversations, while a locally configured LLM (such as Ollama) is dedicated to Smalltalk code generation, ensuring that your source code never leaves your computer.

How to use ClaudeSmalltalk?

Using ClaudeSmalltalk requires four main steps: 1. Obtain the Smalltalk VM and image (Squeak 6.0 is recommended). 2. Install the MCP server into the Smalltalk image. 3. Create a configuration file and set up the Claude Desktop extension. 4. Start interacting with the Smalltalk environment through Claude Desktop. The system will automatically start the VM and establish a connection when needed, eliminating the need for manual management of Smalltalk processes.

Use cases

ClaudeSmalltalk is particularly suitable for the following scenarios: • Smalltalk learners: Learn about Smalltalk classes and methods by asking questions in natural language. • Developers: Quickly browse code libraries, test expressions, and add new methods. • Code review: Let the AI assistant analyze the code and provide improvement suggestions. • Teaching demonstrations: Demonstrate Smalltalk programming concepts in real-time. • Remote development: Connect to a remote Smalltalk environment via MQTT.

Main features

Code evaluation and execution
Execute Smalltalk expressions directly in the running Smalltalk image and obtain results
Class browser
Browse class hierarchies, view methods, instance variables, and class definitions
Method management
Add, modify, and delete methods in classes, and view method source code
Local privacy protection
When using a local LLM such as Ollama, your Smalltalk code never leaves your computer
Automatic VM management
The system automatically starts the Smalltalk VM and establishes a connection when needed
Multi-transport protocol support
Supports both TCP and MQTT connection methods, suitable for local and remote deployments
Image version management
Save the current image or create a new version to protect your development progress
Category navigation
Browse system classes by category to understand the organizational structure of Smalltalk code
Advantages
Fully localized: When using Ollama, all code processing is done locally, ensuring privacy and security.
Real-time interaction: Interact directly with the running Smalltalk environment and immediately see the results of code execution.
Dual architecture: Separate the conversation model from the code generation model to improve accuracy and professionalism.
Easy to set up: Provide detailed configuration guides and example files to simplify the installation process.
Multi-platform support: Supports two mainstream Smalltalk implementations, Squeak and Cuis.
Automatic management: The VM is automatically started and connected, reducing manual operations.
Limitations
macOS permission restrictions: On macOS, the VM and image files must be placed in specific directories (such as /Applications/).
Dependency configuration: Multiple components (VM, image, LLM, Claude Desktop) need to be correctly configured.
Learning curve: Non-Smalltalk users need to understand basic Smalltalk concepts.
Resource requirements: Running a local LLM (such as Ollama) requires sufficient system resources.
Platform-specific: Some configuration steps vary depending on the operating system.

How to use

Obtain the Smalltalk environment
Download the Squeak 6.0 All-in-One package (including the VM and image), or set up the Cuis Smalltalk development environment.
Install the MCP server
Install the MCP server into the Smalltalk image according to the SQUEAK-SETUP.md or CUIS-SETUP.md guide.
Create a configuration file
Copy the example configuration file and modify the VM path and LLM settings according to your environment.
Configure Claude Desktop
Edit the Claude Desktop configuration file and add the smalltalkAgent MCP server configuration.
Start using
Open Claude Desktop and interact with the Smalltalk environment in natural language.

Usage examples

Explore class structures
As a Smalltalk novice, you want to understand the class hierarchy of the system.
Add utility methods
You want to add a helper method to an existing class.
Code debugging
You have a piece of code that doesn't work and need help diagnosing the problem.
Learn best practices
You want to learn common patterns and best practices in Smalltalk.

Frequently Asked Questions

Do I need to pay to use the Claude API?
Will my Smalltalk code be sent to the cloud?
Why can't the VM start on macOS?
Which Smalltalk versions are supported?
How to connect to a remote Smalltalk environment?
Will the system automatically save my changes?

Related resources

Squeak official website
Download the Squeak Smalltalk VM and image
Cuis Smalltalk GitHub
Cuis Smalltalk development repository
Ollama official website
Run large language models locally
SQUEAK-SETUP.md
Detailed guide for setting up the Squeak environment
CUIS-SETUP.md
Detailed guide for setting up the Cuis environment
CLAUDE-README-MCPB.md
Installation guide for the Claude Desktop extension
OpenClaw integration
An alternative way to use Smalltalk via Telegram/Discord
Security audit report
Detailed information on the dual security audit

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "smalltalkAgent": {
      "command": "uv",
      "args": ["run", "/path/to/ClaudeSmalltalk/smalltalk_agent_mcp.py"],
      "env": {
        "SMALLTALK_MCP_CONFIG": "/path/to/smalltalk-mcp.json"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
4.5K
4.5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.3K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.5K
5 points
R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
10.4K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
9.7K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.5K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
10.5K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.4K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
71.7K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.3K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.1K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.0K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.1K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2026AIBase