Code Execution MCP Servers

Containerized environments for coding agents: each agent works in its own fresh container and git branch, with execution history and…

Run untrusted Python/JavaScript code in WebAssembly sandboxes.

Access any API through its existing OpenAPI documentation.

Run JavaScript snippets in isolated Docker sandboxes with on-the-fly npm dependency installation and clean teardown.

Run JavaScript and TypeScript in sandboxed V8 isolates with policy-controlled host capabilities.

Run LLM-generated code in a YepCode sandbox and create custom MCP tools in JavaScript or Python with npm and PyPI packages.

#️⃣ ☁️ - Access any API via its OpenAPI specification, with full JSON Schema support for parameters and request bodies.

Delegate tasks to other AI providers' models, e.g. ask OpenAI to generate an image.

Python runtime interpreter that executes submitted code in an isolated environment.

Control Google Colab notebooks and assign GPUs (T4/L4/A100). Fork of Google's colab-mcp with all tools visible at startup and Windows…

Submit SLURM jobs, run YAML workflows, monitor GPU resources, manage SSH profiles and sync files with local or SSH-remote HPC clusters.

AI-agent programming language. JSON AST in, WASM out. Typed, effect-tracked, Z3-verified.

SWI-Prolog as a logic calculator for LLMs

Execute code through the Piston remote code execution engine.

WasmAgent MCP server — WASM-sandboxed code execution with capability manifests and Tasks API.

Self-hostable GPU-aware job broker: submit, route by VRAM, babysit jobs across machines via MCP.

Code & logic calculator for AI agents: 31 languages, symbolic math, SMT/logic solving, Big-O.

E2B cloud sandboxes: create isolated Linux VMs, clone repos, run commands, manage files and perform git operations without touching the…

MATLAB integration: execute code, run async jobs with progress reporting, get interactive Plotly plots and expose custom .m functions as…

Coding agents build full-stack apps in persistent workspaces and share them by link.

MCP server for Terse, an AI-native code language for coding agents: parse, evaluate, transpile to Python, and token-count Terse source…

Give an agent a real Linux VM: run commands, move files, expose a preview URL, destroy it.

Give any AI assistant a code run button via HackerEarth. 24 languages, zero setup.