MCP Python Interpreter
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_ALLOW_SYSTEM_ACCESS | No | Controls whether the MCP server has system access. Set to 0 to disable system access for security. | 0 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_python_environmentsB | List all available Python environments (system Python and conda environments). |
| list_installed_packagesC | |
| run_python_codeA | |
| run_python_fileB | |
| install_packageB | |
| read_fileA | |
| write_fileB | |
| list_directoryB | |
| clear_sessionC | |
| list_sessionsB | List all active REPL sessions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| python_function_template | Generate a template for a Python function with docstring. |
| refactor_python_code | Help refactor Python code for better readability and performance. |
| debug_python_error | Help debug a Python error. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_environments_resource | List all available Python environments as a resource. |
| get_working_directory_listing | List all Python files in the working directory as a resource. |
TDQS
Scored across 10 tools
Most tools have distinct purposes, but there is some overlap between run_python_code and run_python_file that could cause confusion. The descriptions clarify that run_python_code handles code strings with multiple execution modes, while run_python_file executes existing files via subprocess, but both essentially execute Python code. Other tools like list_directory, read_file, and write_file are clearly distinct.
All tool names follow a consistent verb_noun pattern using snake_case, such as clear_session, install_package, list_directory, etc. There are no deviations in naming conventions, making the set predictable and easy to understand.
With 10 tools, the count is well-scoped for a Python interpreter server. It covers key operations like code execution, file management, package installation, and session handling without being overwhelming or insufficient for the domain.
The tool set provides comprehensive coverage for Python development tasks, including code execution, file operations, package management, and session control. Minor gaps exist, such as no explicit tool for deleting files or uninstalling packages, but agents can work around these using existing tools like write_file with overwrite or other methods.