Pharo NeoConsole
Evaluate Pharo Smalltalk expressions and get system information via a local NeoConsole server.
pharo-nc-mcp-server
A local MCP server to evaluate Pharo Smalltalk expressions and get system information via NeoConsole.
Prerequisites
- Python 3.10 or later
- uv package manager
- Pharo with NeoConsole installed
Pharo Setup
- Install Pharo and NeoConsole
- Set the
PHARO_DIRenvironment variable to your Pharo installation directory (default:~/pharo) - Ensure
NeoConsole.imageis available in the Pharo directory
Installation
- Clone the repository:
git clone <repository-url>
cd pharo-nc-mcp-server
- Install dependencies using uv:
uv sync --dev
Usage
Running the MCP Server
Start the server:
uv run pharo-nc-mcp-server
Cursor MCP settings
{
"mcpServers": {
"pharo-nc-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/your-path/to/pharo-nc-mcp-server",
"run",
"pharo-nc-mcp-server"
]
}
}
}
MCP Tools Available
evaluate_smalltalk_with_neo_console
Execute Smalltalk expressions in Pharo using NeoConsole:
# Example usage in MCP client
evaluate_smalltalk_with_neo_console(expression="42 factorial", command="eval")
evaluate_simple_smalltalk
Execute Smalltalk expressions using Pharo's simple -e option:
# Simple evaluation
evaluate_simple_smalltalk(expression="Time now")
get_pharo_metric
Retrieve system metrics from Pharo:
# Get system status
get_pharo_metric(metric="system.status")
# Get memory information
get_pharo_metric(metric="memory.free")
get_class_comment
Get the comment of a Pharo class:
# Get Array class comment
get_class_comment(class_name="Array")
get_class_definition
Get the definition of a Pharo class:
# Get Array class definition
get_class_definition(class_name="Array")
get_method_list
Get the list of method selectors for a Pharo class:
# Get all method selectors for Array class
get_method_list(class_name="Array")
get_method_source
Get the source code of a specific method in a Pharo class:
# Get source code for Array>>asSet method
get_method_source(class_name="Array", selector="asSet")
Environment Variables
PHARO_DIR: Path to Pharo installation directory (default:~/pharo)
Development
Code Formatting and Linting
# Format code
uv run black pharo_nc_mcp_server/
# Lint code
uv run ruff check pharo_nc_mcp_server/
# Run tests
uv run python -m pytest
# Or use the test script
./scripts/test.sh
Development Scripts
The project includes several convenience scripts in the scripts/ directory:
scripts/format.sh
Formats all code and documentation files in one command:
- Formats Python code using Black
- Formats markdown files using mdformat
- Runs linting checks with Ruff
./scripts/format.sh
scripts/test.sh
Runs the test suite using pytest:
./scripts/test.sh
Servidores relacionados
Scout Monitoring MCP
patrocinadorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
ECharts MCP Server
A server for generating various types of charts using the ECharts library.
CodeGraphContext
An MCP server that indexes local code into a graph database to provide context to AI assistants.
Process Manager MCP
Manage long-running bash processes and persist their logs.
LeetCode
Access LeetCode problems, user information, and contest data.
Debugger MCP Server
A development tool for real-time debugging, code quality monitoring, and AI insights for React/Next.js applications.
MCP Low-Level Server Streamable HTTP
A low-level MCP server implementation with streamable HTTP support, configured via environment variables.
Vercel AI SDK MCP Server Project
An MCP server for the Vercel AI SDK, enabling integrations with Figma and 21st.dev Magic.
TMUX
Lets agents create sessions, split panes, run commands, and capture output with TMUX
Union - Unity MCP Server
An MCP server for managing and interacting with Unity projects.
Reloaderoo
A local MCP server for developers that mirrors your in-development MCP server, allowing seamless restarts and tool updates so you can build, test, and iterate on your MCP server within the same AI session without interruption.