elusznik/mcp-server-code-execution-mode
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.
This helps developers integrate many different software tools with large language models (LLMs) more efficiently. It takes a description of various tools and allows the LLM to write Python code to interact with them, significantly reducing the amount of information the LLM needs to process upfront. This makes it easier and cheaper for AI/ML engineers and platform architects to build intelligent agents that can use a vast array of specialized services.
317 stars.
Use this if you are building an LLM agent that needs to interact with many external tools or services, especially if those tools are built on Python or require secure, isolated execution environments.
Not ideal if your LLM agent only uses a few simple tools and doesn't require a high degree of security isolation or complex Python-based data processing.
Stars
317
Forks
28
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/elusznik/mcp-server-code-execution-mode"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gradion-ai/ipybox
Python code execution sandbox with programmatic MCP tool calling (PTC)
BlackSnufkin/LitterBox
A secure sandbox environment for malware developers and red teamers to test payloads against...
universal-tool-calling-protocol/code-mode
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
Kiln-AI/Kilntainers
MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.
buremba/1mcp
Let your agent write code and execute code directly in the browser with WASM