Skip to main content
Glama
enesjakozh
maxim-saplin

Safe Local Python Executor/Interpreter

by maxim-saplin
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Safe Local Python Executor

An MCP server (stdio transport) that wraps Hugging Face's LocalPythonExecutor (from the smolagents framework). It is a custom Python runtime that provides basic isolation/security when running Python code generated by LLMs locally. It does not require Docker or VM. This package allows to expose the Python executor via MCP (Model Context Protocol) as a tool for LLM apps like Claude Desktop, Cursor or any other MCP compatible client. In case of Claude Desktop this tool is an easy way to add a missing Code Interpreter (available as a plugin in ChatGPT for quite a while already).

Features

  • Exposes run_python tool

  • Safer execution of Python code compared to direct use of Python eva()l

  • Ran via uv in Python venv

  • No file I/O ops are allowed

  • Restricted list of imports

    • collections

    • datetime

    • itertools

    • math

    • queue

    • random

    • re

    • stat

    • statistics

    • time

    • unicodedata

Related MCP server: MCP Code Mode

Security

Be careful with execution of code produced by LLM on your machine, stay away from MCP servers that run Python via command line or using eval(). The safest option is using a VM or a docker container, though it requires some effort to set-up, consumes resources/slower. There're 3rd party servcices providing Python runtime, though they require registration, API keys etc.

LocalPythonExecutor provides a good balance between direct use of local Python environment (which is easier to set-up) AND remote execution in Dokcer container or a VM/3rd party service (which is safe). Hugginng Face team has invested time into creating a quick and safe option to run LLM generated code used by their code agents. This MCP server builds upon it:

To add a first layer of security, code execution in smolagents is not performed by the vanilla Python interpreter. We have re-built a more secure LocalPythonExecutor from the ground up.

Read more here.

Installation and Execution

Installing via Smithery

To install Safe Local Python Executor for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @maxim-saplin/mcp_safe_local_python_executor --client claude

Installing Manually

  1. Install uv (e.h. brew install uv on macOS or use official docs)

  2. Clone the repo, change the directory cd mcp_safe_local_python_executor

  3. The server can be started via command line uv run mcp_server.py, venv will be created automatically, depedencies (smollagents, mcp) will be installed

Configuring Claude Desktop

  1. Make sure you have Claude for Desktop installed (download from claude.ai)

  2. Edit your Claude for Desktop configuration file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • Windows: %APPDATA%\Claude\claude_desktop_config.json

    • Or open Claude Desktop -> Settings -> Developer -> click "Edit Config" button

  3. Add the following configuration:

{
    "mcpServers": {
        "safe-local-python-executor": {
            "command": "uv",
            "args": [
                "--directory", 
                "/path/to/mcp_local_python_executor/",
                "run",
                "mcp_server.py"
            ]
        }
    }
}

  1. Restart Claude for Desktop

  2. The Python executor tool will now be available in Claude (you'll see hammer icon in the message input field)

Example Prompts

Once configured, you can use prompts like:

  • "Calculate the factorial of 5 using Python"

  • "Create a list of prime numbers up to 100"

  • "Solve this equation (use Python): x^2 + 5x + 6 = 0"

Development

Clone the repo. Use uv to create venv, install dev dependencies, run tests:

uv venv .venv
uv sync --group dev
python -m pytest tests/

Available Tools

1 tool
run_pythonA

Execute Python code in a secure sandbox environment.

This tool allows running simple Python code for calculations and data manipulations.
The execution environment is restricted for security purposes. Make sure you create a single file
that can be executed in one go and it returns a result.

Default allowed imports:
- math
- random 
- datetime
- time
- json
- re
- string
- collections
- itertools
- functools
- operator

Args:
    code: The Python code to execute. Must be valid Python 3 code. The result must be stored in a variable called `result`. E.g.:
    ```python
    import math
    result = math.sqrt(16)
    ```
    
Returns:
    A dictionary with execution results containing:
    - result: The final value or None if no value is returned
    - logs: Any output from print statements
ParametersJSON Schema
NameRequiredDescriptionDefault
codeYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key traits: the secure sandbox environment, restrictions for security, requirement to create a single executable file, and default allowed imports. However, it doesn't cover aspects like execution time limits, memory constraints, or error handling, leaving some behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded with the core purpose, followed by usage notes, allowed imports, parameter details, and return information. It's appropriately sized for the tool's complexity, but the list of allowed imports and code example add some length that could be streamlined without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (code execution with security constraints), no annotations, and an output schema that documents return values, the description is highly complete. It covers purpose, behavioral traits, parameter semantics with examples, and usage context, leaving minimal gaps for an AI agent to understand and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the description must fully compensate. It adds substantial meaning beyond the schema by detailing the 'code' parameter: it must be valid Python 3 code, require storing results in a variable called 'result', and includes a clear example with syntax and usage. This provides comprehensive semantic context for the single parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Execute Python code in a secure sandbox environment' with specific verbs ('execute', 'run') and resource ('Python code'). It distinguishes the tool's scope by mentioning it's for 'simple Python code for calculations and data manipulations' and operates in a restricted environment, making its function unambiguous even without siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by specifying it's for 'simple Python code for calculations and data manipulations' and mentions security restrictions, but it lacks explicit guidance on when to use this tool versus alternatives (e.g., other code execution tools or manual methods). No siblings are listed, so differentiation isn't needed, but general usage context is only partially addressed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool update
    • First observedrun_python
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'run_python' has a clearly defined and distinct purpose.

Naming Consistency5/5

The naming follows a consistent verb_noun pattern with 'run_python'. Since there's only one tool, consistency is inherently perfect with no deviations to assess.

Tool Count2/5

A single tool is too few for the server's purpose as a 'Safe Local Python Executor/Interpreter'. This suggests a thin surface that may lack essential operations like code validation, environment inspection, or error handling, limiting agent functionality.

Completeness2/5

The tool set is severely incomplete for the domain. While 'run_python' covers execution, there are obvious gaps such as tools for listing allowed imports, checking code safety, managing execution timeouts, or handling errors, which are critical for a secure interpreter.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • MCP Code Mode

    anaseqal
    A
    license
    A
    quality
    D
    maintenance
    Universal Python code execution MCP server that lets LLMs write and run Python for any task, with auto-install packages, streaming output, and automatic file display.
    9
    1
    MIT

  • tjariy-code-interpreter-mcp

    jariy17
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that provides secure code execution capabilities using AWS Bedrock AgentCore's CodeInterpreter, supporting Python, JavaScript, TypeScript, shell commands, and file operations.
    13
    MIT

  • ChatGPT Desktop Commander MCP

    kathirm1323-ai
    F
    license
    Not graded
    quality
    B
    maintenance
    A Python MCP server that allows ChatGPT to execute commands on your local PC via a secure Cloudflare tunnel.
    -

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/maxim-saplin/mcp_safe_local_python_executor'

If you have feedback or need assistance with the MCP directory API, please join our Discord server