Sandboxed Python execution with automatic dependency management. Executes Python scripts in isolated environments (bubblewrap or Docker) with PEP 723 inline dependencies, preventing host pollution.
Enables AI agents to perform federated data transfers and remote code execution on HPC endpoints via Globus, wrapping the Globus CLI and Globus Compute SDK.
Enables AI assistants and developers to analyze code for language-specific best practices and idiomatic patterns across programming languages, CI automation, and configuration formats.
Enables users to create, manage, and execute Google Apps Script projects through natural language. It provides comprehensive tools for code editing, function execution, deployment management, and monitoring script processes.
An MCP server that bridges local AI agents to Google Colab notebooks, enabling execution of Python code and interaction with notebook states directly from the agent.
An MCP server that provides a toolbox for interacting with EPA SWMM stormwater models, enabling users to analyze model data and interpret results through LLM-driven tools. It assists stormwater modelers in understanding hydraulic systems and modeling behavior using natural language interfaces.
Enables code execution in 70+ programming languages and databases through the Onecompiler API, allowing users to run and test code directly from their MCP-enabled applications.
PhysBound is a specialized "Physics Linter" for AI that deterministically validates RF and thermodynamic claims against hard physical limits, preventing hallucinations in engineering workflows.
A personal memory engine and MCP server that stores durable facts in markdown files managed via git, enabling hybrid search (lexical + semantic) through an MCP interface for persistent context across LLM sessions.
Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.
Enables AI assistants to render 3D models from OpenSCAD code, generating single views or multiple perspectives with full camera control. Supports animations, custom parameters, and returns base64-encoded PNG images for seamless integration.