15 boosters for "sandbox" — open source, verified from GitHub, ready to install
"name": "context-mode", "version": "1.0.75", "description": "MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.",
Context Mode is an MCP server that dramatically reduces Claude's context window consumption through sandboxed code execution and intelligent full-text search, enabling developers to work with larger codebases and knowledge bases without hitting token limits.
Alias for tech-debt research
Use this agent when documentation in the `architecture/` directory needs to be updated or created for a specific file after implementing a feature, fix, refactor, or behavior change. Launch one instance of this agent per file that needs updating. This agent maintains the *contents* of architecture documentation files — it does not decide which files exist or how the directory is organized.\n\nExamples:\n\n- Example 1:\n Context: A developer just finished implementing OPA policy evaluation in the sandbox system.\n user: "I just finished implementing the OPA engine in crates/openshell-sandbox/src/opa.rs. Update architecture/sandbox.md to reflect the new policy evaluation flow."\n assistant: "I'll launch the arch-doc-writer agent to update the sandbox architecture documentation with the new OPA policy evaluation details."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/sandbox.md>\n\n- Example 2:\n Context: A refactor changed how the HTTP CONNECT proxy handles allowlists.\n user: "The proxy allowlist logic was refactored. Please update architecture/proxy.md."\n assistant: "Let me use the arch-doc-writer agent to synchronize the proxy documentation with the refactored allowlist logic."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/proxy.md>\n\n- Example 3:\n Context: After implementing a new CLI command, the assistant proactively updates docs.\n user: "Add a --rego-policy flag to the CLI."\n assistant: "Here is the implementation of the --rego-policy flag."\n <implementation complete>\n assistant: "Now let me launch the arch-doc-writer agent to update the CLI architecture documentation with the new flag."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/cli.md>\n\n- Example 4:\n Context: A user wants high-level overview documentation for a non-engineering audience.\n user: "Update architecture/overview.md with a non-engineer-friendly explanation of the sandbox system."\n assistant: "I'll launch the arch-doc-writer agent to create an accessible overview of the sandbox system for non-technical readers."\n <uses Task tool to launch arch-doc-writer with audience=non-engineer directive>\n\n- Example 5:\n Context: Multiple files need updating after a large feature lands.\n user: "I just landed the network namespace isolation feature. Update architecture/sandbox.md and architecture/networking.md."\n assistant: "I'll launch two arch-doc-writer agents — one for each file — to update the documentation in parallel."\n <uses Task tool to launch arch-doc-writer for architecture/sandbox.md>\n <uses Task tool to launch arch-doc-writer for architecture/networking.md>
"name": "tensorlake", "description": "Tensorlake SDK for agent sandboxes and sandbox-native orchestration. Use when building AI agents that need sandboxed execution environments, isolated tool calls, or durable workflow orchestration.", "author": "TensorLake",
Secure agent runtime with trusted process mediation
sf-deploy automates Salesforce DevOps workflows including metadata deployments, org management, and CI/CD pipeline setup using Salesforce CLI v2. Developers managing Salesforce projects benefit from guided deployment automation and troubleshooting.
"name": "agentkernel", "description": "Run commands in secure, isolated sandboxes using agentkernel", "author": "Paul Thrasher",
An autonomous coding agent that delegates tasks to Codex CLI with configurable risk modes (full-auto, sandbox, YOLO) to iteratively debug and test code until it passes. Developers building automated code generation and testing pipelines benefit most from this booster.
A CLI tool for orchestrating AI agents at scale to analyze code repositories, manage GitHub collaborators, and conduct bulk research across multiple data sources including Notion and CSV. Ideal for developers and teams automating large-scale code analysis, data processing, and repository management tasks.
Spotdb is an ephemeral data sandbox for AI workflows that provides secure, isolated database environments for agentic AI systems. It's useful for developers building AI agents and LLM applications that need safe data isolation and guardrails.
A Node.js MCP server that executes JavaScript code safely in isolated Docker containers with on-demand npm dependency installation. Developers and AI agents benefit from secure, sandboxed code execution capabilities integrated into Claude.
Clawgram is a photo-first social network designed for AI agents to share images and interact within a secure, sandboxed environment. It benefits AI developers building multi-agent systems that need safe social collaboration features.
Node Code Sandbox MCP enables AI agents and LLMs to safely execute JavaScript code, install npm packages, and test implementations in real-time. Developers building coding assistants, automated testing tools, and interactive AI applications benefit from this secure, MCP-compliant execution environment.
STUzhy Py_execute_mcp enables developers to run Python code in a secure sandbox environment without local setup, with support for inline dependency declaration. Ideal for rapid prototyping, testing, and integration with Claude AI workflows.
