Execute Python code in a sandboxed environment based on natural language prompts. Generate and run code, then return both the code and execution results.
MIT
606,387 tools. Updated 2026-09-24 07:42
"How to run a Python script in a sandboxed environment" matching MCP tools:
- Execute code securely in a sandboxed environment supporting Python, JavaScript, Bash, and R, for $0.005 per execution.MIT
- Run Python, JavaScript, or TypeScript code securely in a sandboxed environment. Execute code snippets with isolated resources for safe testing.MIT
- Create a DAT in TouchDesigner preloaded with Python code, choosing a text, execute, or script type to control how the code runs.MITDestructive
- Generate a Meep FDTD simulation script from a natural-language problem description. Returns runnable Python and an explanation; pass a previous error trace to patch failed runs.MIT
- Execute a Python FLOX strategy against a CSV dataset in a sandboxed subprocess and return backtest statistics as JSON.MIT
Matching MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.4-
- AlicenseAqualityDmaintenanceMCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.11MIT
Matching MCP Connectors
Run Python code from natural language prompts, with optional PyPI package install.
AI agents hire a human to observe, log or film on site. Typed results, feasibility before payment.
- Export a session as a runnable Python script that regenerates the model, drawings, and simulations, with checks and provenance for every computed result.Apache 2.0
- Execute Python code in a secure sandbox environment for calculations and data manipulation. The tool runs simple Python scripts with restricted imports and returns results with logs.MIT
- Run DML for selected nodes in a deployed cloud environment to refresh data. Requires explicit confirmation before execution.MITDestructive
- Execute Python code in a sandboxed environment with numerical libraries, return exported results, and include verification certificates and diagnostics for solver outputs.MIT
- Run a local .mjs file and record it as a script step in an active flow. Use when a local script is requested, passing the same flow name and project root.Apache 2.0
- Execute Python code in a sandboxed environment with JAX and model fitting libraries, using export() to return results. Use for running generated or custom model fitting code.MIT
- Run a sandboxed script under specified chaos faults to identify failure events. Pinpoint system weaknesses by injecting faults and observing outcomes.MITDestructive
- Write UTF-8 text files to the workflow workspace, enabling agents to persist scripts, data, or outputs within a sandboxed environment.Apache 2.0
- Execute Python code in a restricted subprocess to deterministically verify math, logic, and code analysis tasks using symbolic engines.Apache 2.0
- Execute a method in a sandboxed environment by providing file and method UUIDs. Returns output, success, error, and optional benchmark data.MIT
- Register a Python function with Globus Compute to enable remote execution. Then submit tasks to run the function on compute endpoints.Apache 2.0
- Execute bash commands in a sandboxed environment. Use session IDs to maintain working directory, environment, and filesystem state across commands.Apache 2.0
- Create a TouchDesigner DAT node preloaded with your Python code, choosing between text, execute, or script types. Stores code as a node for later execution.MITDestructive
- Run a skill's bundled script: list available ones, then execute with optional key-value inputs in a sandbox with 30-second timeout.Apache 2.0
- Submit a Python script for background execution in PFC. Get a task ID to poll progress, cancel, or modify variables mid-run using companion tools.MIT