Skip to main content
skill CX Codex

mcp-code-execution-mode — Claude Code skill: setup & usage

mcp-code-execution-mode executes Python inside rootless containers and routes calls to MCP servers to keep token consumption minimal.

no license 174 installs ★ 9 updated 2026-10-09

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add reason-machines/mcp-skills --skill mcp-code-execution-mode -a claude-code
Open on GitHub

What mcp-code-execution-mode does

Large tool catalogs can consume tens of thousands of tokens per turn. This component replaces heavy schema dumps with a single run_python entry point. The agent queries tools dynamically at runtime via helper methods like search_tool_docs and triggers actions programmatically, keeping setup overhead around 200 tokens.

Execution takes place inside an isolated sandbox with a read-only filesystem, blocked network access, and a default memory boundary of 512m. Sessions stay persistent across runs, so dataframes and written files remain accessible when MCP_BRIDGE_SESSION_PERSIST is active.

Running this bridge requires Python 3.11+ alongside an active Podman or Docker Desktop engine. Without an operational container runtime, code execution calls fail immediately.

What it helps with

  • reduce token overhead from large MCP tool schema sets
  • execute Python logic inside isolated rootless sandboxes
  • search and load external tool definitions on demand
  • orchestrate multiple MCP servers from a single script

Example prompts for the agent

  • Run python code in a sandbox to query open issues from GitHub
  • Discover mcp tools dynamically and process sales data from the filesystem
  • Execute an isolated Python script with persistent session state

How to install mcp-code-execution-mode

1Skills CLI (Vercel)

npx skills add reason-machines/mcp-skills --skill mcp-code-execution-mode -a claude-code

2Manually: put the files in place

~/.claude/skills/mcp-code-execution-mode/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/mcp-code-execution-mode/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about mcp-code-execution-mode

How to install mcp-code-execution-mode in Claude Code?

Run npx skills add reason-machines/mcp-skills --skill mcp-code-execution-mode -a claude-code. The definition is placed into ~/.claude/skills/mcp-code-execution-mode/SKILL.md.

What does mcp-code-execution-mode do?

It proxies external stdio MCP tools through Python running inside a container, fetching tool schemas only when the agent explicitly requests them.

What dependencies are necessary to start the environment?

You need Python 3.11 or newer together with an initialized Podman machine or running Docker Desktop instance.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set98

The whole set →
alpaca-mcp-server-trading alpaca-mcp-server-trading connects the Alpaca MCP server to your AI coding agent to execute trades, check account balances, and fetch live market quotes in natural language. CX Codex +1 185installs anki-mcp-server-integration anki-mcp-server-integration connects your AI agent to desktop Anki via Model Context Protocol to review spaced repetition cards, create notes in batches, and manage decks. CX Codex +1 180installs linux-mcp-server-administration The linux-mcp-server-administration skill gives Claude Code read-only Linux diagnostics through MCP and SSH. Use it to inspect RHEL-based hosts, services, logs, processes, networking, and storage. CX Codex +1 178installs mcp-server-spec-driven-development The mcp-server-spec-driven-development skill guides a project from EARS requirements to a design document and generated code. Use it when you want those steps to build on one another. CX Codex +1 175installs mcp-server-code-execution-mode mcp-server-code-execution-mode executes Python in rootless Podman or Docker containers and proxies MCP tools through a single entry point, cutting context from 30,000 to 200 tokens. CX Codex +1 173installs nanobanana-mcp-image-generation The nanobanana-mcp-image-generation skill connects an agent to Gemini image generation and editing with model selection, 4K output, aspect ratios, and templates. Use it for visual assets from a coding workspace. CX Codex +1 172installs mcp-server-bash-sdk mcp-server-bash-sdk guides you in building zero-runtime Model Context Protocol servers using pure Bash and jq instead of heavy runtimes. CX Codex +1 171installs codex-mcp-server-integration codex-mcp-server-integration — a skill that bridges OpenAI Codex CLI to Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode via MCP. Brings code analysis, generation, branch review, and web search into the editor. CX Codex +1 171installs

Project sponsors

Companies that keep this analytics open