MCP Code Executor MCP Server

execute code. Exposed over MCP by the mcp code executor mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

The MCP Code Executor is an MCP server that allows LLMs to execute Python code within a specified Python environment. This enables LLMs to run code with access to libraries and dependencies defined in the environment. It also supports incremental code generation for handling large code blocks that may exceed token limits.

• Execute Python code from LLM prompts
• Support for incremental code generation to overcome token limitations
• Run code within a specified environment (Conda, virtualenv, or UV virtualenv)
• Install dependencies when needed
• Check if packages are already installed
• Dynamically configure the environment at runtime

Configuration

You will need 5 environment variables: CODE_STORAGE_DIR, ENV_TYPE, CONDA_ENV_NAME, VENV_PATH, UV_VENV_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

• Node.js installed - One of the following: - Conda installed with desired Conda environment created - Python virtualenv - UV virtualenv

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. It is maintained by bazinga012; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP Code Executor's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp code executor mcp server does with a few real requests.