Explore
Contribute
Sign In

Explore

  1. Explore
  2. /
  3. Productivity & Collaboration
  4. /
  5. Python Interpreter

Python Interpreter

Python Interpreter

mcp

A Python-based execution tool that mimics a Jupyter notebook environment. It accepts code snippets, executes them, and maintains state across sessions — preserving variables, imports, and past results. Ideal for iterative development, debugging, or code execution.

3.2K

1 Tool

Packaged by
Add to Docker Desktop

Version 4.43 or later needs to be installed to add the server automatically

OverviewTools (1)Manual installation
Docker Hub⁠Github repository⁠

Use cases

Executes Python code within a persistent session, retaining past results (e.g., variables, imports). Similar to a Jupyter notebook. A session_id is returned on first use and must be included in subsequent requests to maintain context.

About

Python Interpreter MCP Server

A Python-based execution tool that mimics a Jupyter notebook environment. It accepts code snippets, executes them, and maintains state across sessions — preserving variables, imports, and past results. Ideal for iterative development, debugging, or code execution.

What is an MCP Server?⁠

Characteristics

AttributeDetails
Docker Imagemcp/mcp-code-interpreter⁠
Authorakuadane⁠
Repositoryhttps://github.com/akuadane/mcp-code-interpreter⁠
Dockerfilehttps://github.com/akuadane/mcp-code-interpreter/blob/main/Dockerfile⁠
Docker Image built byDocker Inc.
Docker Scout Health ScoreDocker Scout Health Score
Verify SignatureCOSIGN_REPOSITORY=mcp/signatures cosign verify mcp/mcp-code-interpreter --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
LicenceMIT License

Available Tools (1)

Tools provided by this ServerShort Description
execute_codeExecutes Python code within a persistent session, retaining past results (e.g., variables, imports).

Tools Details

Tool: execute_code

Executes Python code within a persistent session, retaining past results (e.g., variables, imports). Similar to a Jupyter notebook. A session_id is returned on first use and must be included in subsequent requests to maintain context.

ParametersTypeDescription
codestring
session_idintegeroptional

Use this MCP Server

{
  "mcpServers": {
    "mcp-code-interpreter": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/local-directory:/local-directory",
        "mcp/mcp-code-interpreter"
      ]
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠

Manual installation

You can install the MCP server using:

​

Installation for

Related servers

© 2025 Docker, Inc. All rights reserved. | Terms of Service | Subscription Service Agreement | Privacy | Legal