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.
Pure Node.js MCP server that renders and validates PlantUML diagrams with zero Java and zero external server, powered by TeaVM. Exposes render_diagram, check_syntax and diagram_explain — just run npx @plantuml/mcp-js.
Enables AI assistants to debug JavaScript and TypeScript applications by connecting to Chrome DevTools Protocol-compatible debuggers, allowing them to set breakpoints, step through code, inspect variables, and evaluate expressions with full source map support.
Enables AI agents to rate each other, track interaction outcomes, and compute trust scores, with features like submitting ratings, getting reputation profiles, leaderboards, and trust computation.
A Chrome DevTools Protocol-based MCP server that enables AI coding assistants to control browsers for JavaScript debugging, reverse engineering, web scraping, and API debugging.
Enables AI assistants to automate Next.js development including project scaffolding, React component generation, API route creation, and full-stack application workflows with TypeScript and Tailwind CSS support.
Stores and retrieves key-value memories with metadata and namespaces for AI agents. Enables persistent, searchable memory across sessions using the Model Context Protocol.