# Python Execute Server
A Model Context Protocol (MCP) server that provides Python code execution capabilities for Large Language Models (LLMs).
## Features
- **Python Code Execution**: Execute Python code in a persistent REPL environment
- **Data Analysis Support**: Perform calculations and data analysis with full Python ecosystem
- **File Output**: Automatically save executed code to timestamped files
- **Workspace Integration**: Execute code within a designated workspace directory
- **Error Handling**: Comprehensive error reporting and exception handling
- **Output Capture**: Capture and return both stdout and execution results
## Tools Provided
- `python_repl_tool`: Execute Python code and perform data analysis or calculations with visible output
## Execution Features
### Code Execution
- Persistent REPL environment maintains state between executions
- Support for all Python standard library modules
- Data analysis and scientific computing capabilities
- Real-time output capture and display
### File Management
- Automatic code saving with unique timestamped filenames
- Organized file storage in workspace/python directory
- Code preservation for debugging and reference
### Output Handling
- Stdout capture for print statements and output
- Error detection and reporting
- Structured result formatting
- Multi-format result support
## Configuration Options
- `--workspace-path`: Set the workspace directory (default: ./workspace)
## Server Configuration
To use this server with MCP clients, add the following configuration to your MCP settings:
For development or when using `uv`:
```json
{
"mcpServers": {
"python-execute-server": {
"command": "uv",
"args": ["--directory", "directory_of_python-execute-server", "run", "python-execute-server", "--workspace-path", "/path/to/your/workspace"],
"env": {}
}
}
}
```
## Usage Examples
### Basic Code Execution
```python
# Execute simple calculations
result = await python_repl_tool("print(2 + 2)")
# Output: Successfully executed code with Stdout: 4
```
### Data Analysis
```python
# Perform data analysis
code = """
import pandas as pd
import numpy as np
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
print(df.describe())
"""
result = await python_repl_tool(code)
```
### Mathematical Calculations
```python
# Complex mathematical operations
code = """
import math
result = math.sqrt(16) + math.pi
print(f"Result: {result}")
"""
result = await python_repl_tool(code)
```
## REPL Environment
### Persistent State
- Variables and imports persist between executions
- Allows for multi-step data analysis workflows
- State maintained throughout session
### Library Support
- Full access to Python standard library
- Support for popular data science libraries (pandas, numpy, matplotlib, etc.)
- Extensible with additional package installations
### Error Handling
- Graceful error capture and reporting
- Exception details preserved and returned
- Non-blocking error handling
## File Output System
### Automatic Saving
- All executed code automatically saved to files
- Unique filenames with timestamp and random suffix
- Organized storage in workspace/python directory
### File Naming Convention
```
replaceChatId_{timestamp}_{random_number}.py
```
### Output Tracking
- File paths returned in execution results
- Support for multiple output formats
- Integration with file management systems
## Safety Features
- **Workspace Isolation**: Code execution contained within workspace
- **Error Containment**: Exceptions don't crash the server
- **Input Validation**: Code input validation and sanitization
- **Resource Management**: Proper cleanup and resource handling
## Use Cases
- **Data Analysis**: Statistical analysis and data processing
- **Mathematical Calculations**: Complex mathematical operations
- **Prototyping**: Quick code testing and validation
- **Educational**: Learning and experimenting with Python
- **Automation**: Script execution and task automation
## License
MIT License - see LICENSE file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "iflow-mcp_python-execute-server",
"maintainer": null,
"docs_url": null,
"requires_python": "==3.12.7",
"maintainer_email": null,
"keywords": "automation, code, llm, mcp, python",
"author": "iflow team",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/1b/f8/db2c0df0816315d1cd8845190d2d38958e9c1e16444266b56dc881cf4ab7/iflow_mcp_python_execute_server-0.1.2.tar.gz",
"platform": null,
"description": "# Python Execute Server\n\nA Model Context Protocol (MCP) server that provides Python code execution capabilities for Large Language Models (LLMs).\n\n## Features\n\n- **Python Code Execution**: Execute Python code in a persistent REPL environment\n- **Data Analysis Support**: Perform calculations and data analysis with full Python ecosystem\n- **File Output**: Automatically save executed code to timestamped files\n- **Workspace Integration**: Execute code within a designated workspace directory\n- **Error Handling**: Comprehensive error reporting and exception handling\n- **Output Capture**: Capture and return both stdout and execution results\n\n## Tools Provided\n\n- `python_repl_tool`: Execute Python code and perform data analysis or calculations with visible output\n\n## Execution Features\n\n### Code Execution\n- Persistent REPL environment maintains state between executions\n- Support for all Python standard library modules\n- Data analysis and scientific computing capabilities\n- Real-time output capture and display\n\n### File Management\n- Automatic code saving with unique timestamped filenames\n- Organized file storage in workspace/python directory\n- Code preservation for debugging and reference\n\n### Output Handling\n- Stdout capture for print statements and output\n- Error detection and reporting\n- Structured result formatting\n- Multi-format result support\n\n## Configuration Options\n\n- `--workspace-path`: Set the workspace directory (default: ./workspace)\n\n## Server Configuration\n\nTo use this server with MCP clients, add the following configuration to your MCP settings:\n\nFor development or when using `uv`:\n\n```json\n{\n \"mcpServers\": {\n \"python-execute-server\": {\n \"command\": \"uv\",\n \"args\": [\"--directory\", \"directory_of_python-execute-server\", \"run\", \"python-execute-server\", \"--workspace-path\", \"/path/to/your/workspace\"],\n \"env\": {}\n }\n }\n}\n```\n\n## Usage Examples\n\n### Basic Code Execution\n```python\n# Execute simple calculations\nresult = await python_repl_tool(\"print(2 + 2)\")\n# Output: Successfully executed code with Stdout: 4\n```\n\n### Data Analysis\n```python\n# Perform data analysis\ncode = \"\"\"\nimport pandas as pd\nimport numpy as np\n\ndata = {'A': [1, 2, 3], 'B': [4, 5, 6]}\ndf = pd.DataFrame(data)\nprint(df.describe())\n\"\"\"\nresult = await python_repl_tool(code)\n```\n\n### Mathematical Calculations\n```python\n# Complex mathematical operations\ncode = \"\"\"\nimport math\nresult = math.sqrt(16) + math.pi\nprint(f\"Result: {result}\")\n\"\"\"\nresult = await python_repl_tool(code)\n```\n\n## REPL Environment\n\n### Persistent State\n- Variables and imports persist between executions\n- Allows for multi-step data analysis workflows\n- State maintained throughout session\n\n### Library Support\n- Full access to Python standard library\n- Support for popular data science libraries (pandas, numpy, matplotlib, etc.)\n- Extensible with additional package installations\n\n### Error Handling\n- Graceful error capture and reporting\n- Exception details preserved and returned\n- Non-blocking error handling\n\n## File Output System\n\n### Automatic Saving\n- All executed code automatically saved to files\n- Unique filenames with timestamp and random suffix\n- Organized storage in workspace/python directory\n\n### File Naming Convention\n```\nreplaceChatId_{timestamp}_{random_number}.py\n```\n\n### Output Tracking\n- File paths returned in execution results\n- Support for multiple output formats\n- Integration with file management systems\n\n## Safety Features\n\n- **Workspace Isolation**: Code execution contained within workspace\n- **Error Containment**: Exceptions don't crash the server\n- **Input Validation**: Code input validation and sanitization\n- **Resource Management**: Proper cleanup and resource handling\n\n## Use Cases\n\n- **Data Analysis**: Statistical analysis and data processing\n- **Mathematical Calculations**: Complex mathematical operations\n- **Prototyping**: Quick code testing and validation\n- **Educational**: Learning and experimenting with Python\n- **Automation**: Script execution and task automation\n\n## License\n\nMIT License - see LICENSE file for details.",
"bugtrack_url": null,
"license": "MIT",
"summary": "A Model Context Protocol server providing python code execution capability",
"version": "0.1.2",
"project_urls": null,
"split_keywords": [
"automation",
" code",
" llm",
" mcp",
" python"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "45fcc74aad60de84a6df6d11f6bb9ad4f037e2b47f48406abc06147e6a159999",
"md5": "9cef70335dd0d2e37a07f5736aec9c09",
"sha256": "629104ebcbc77affbee77939ebb51a4ef0ef932135022070a008b761fd9ced8e"
},
"downloads": -1,
"filename": "iflow_mcp_python_execute_server-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9cef70335dd0d2e37a07f5736aec9c09",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "==3.12.7",
"size": 250007,
"upload_time": "2025-09-01T09:34:57",
"upload_time_iso_8601": "2025-09-01T09:34:57.583439Z",
"url": "https://files.pythonhosted.org/packages/45/fc/c74aad60de84a6df6d11f6bb9ad4f037e2b47f48406abc06147e6a159999/iflow_mcp_python_execute_server-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "1bf8db2c0df0816315d1cd8845190d2d38958e9c1e16444266b56dc881cf4ab7",
"md5": "741cac2565ffcdede7fc8d054b7992b2",
"sha256": "7c829f4a8b49f8ae279da415b8c1a4840403ee571d23001f74026da10675b765"
},
"downloads": -1,
"filename": "iflow_mcp_python_execute_server-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "741cac2565ffcdede7fc8d054b7992b2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "==3.12.7",
"size": 247280,
"upload_time": "2025-09-01T09:34:59",
"upload_time_iso_8601": "2025-09-01T09:34:59.121691Z",
"url": "https://files.pythonhosted.org/packages/1b/f8/db2c0df0816315d1cd8845190d2d38958e9c1e16444266b56dc881cf4ab7/iflow_mcp_python_execute_server-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-01 09:34:59",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "iflow-mcp_python-execute-server"
}
JSON