Antigravity CLI Integrations

Model Context Protocol (MCP) is an open protocol designed to standardize how applications provide context to large language models (LLMs). It acts as a universal connector, similar to a USB-C port, allowing LLMs to seamlessly integrate with various data sources and tools. MCP supports a client-server architecture, enabling programs (clients) to interact with lightweight servers that expose specific capabilities. With growing pre-built integrations and flexibility to switch between LLM vendors, MCP helps users build complex workflows and AI agents while ensuring secure data management within their infrastructure.

Google Antigravity is an agentic development platform that reimagines the traditional IDE for the AI-first era. Designed for developers of all levels, it enables seamless collaboration between humans and intelligent agents across the editor, terminal, and browser. The platform allows developers to issue natural language commands, monitor autonomous coding workflows, and review generated artifacts—all from a unified interface. Antigravity introduces cross-surface agent synchronization, ensuring consistency and context sharing across multiple workspaces. Its mission control view lets users manage and refine multiple agents simultaneously, making complex development tasks faster, smarter, and more intuitive. Whether you’re building enterprise-scale systems or experimenting creatively, Google Antigravity elevates the development experience into a new era of agent-driven productivity.

Graphify is an open source knowledge graph engine that turns any input, including code, docs, papers, meetings, images, browser tabs, and commits, into one traversable graph with complete recall. It is built as persistent memory for AI coding assistants, giving tools like Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, Aider, Factory Droid, Kimi Code, Kiro, Pi, and Google Antigravity a queryable understanding of a project instead of making them repeatedly grep through files. Users can point Graphify at any directory, and it builds an initial corpus through AST extraction, semantic analysis, and Leiden clustering, transforming an entire codebase or document corpus into a graph in one pass. Unlike RAG pipelines that re-embed everything on every change, Graphify maintains a living graph that updates only affected nodes and edges when files change, allowing the rest of the corpus to stay intact even at enterprise scale.

MemPalace is a local-first storage and retrieval system for AI workflows, built to give AI a memory while keeping the user’s words under their own control. It stores conversations verbatim instead of reducing them to summaries, then organizes that memory into a navigable “palace” structure inspired by the ancient memory palace technique. Conversations can be arranged into wings for people, projects, or topics, with rooms and drawers used to make information easier to locate, narrow, and retrieve later. It is designed for people who believe their words are theirs, with local-first storage, zero telemetry, and a privacy-focused approach that keeps memory on the user’s machine. MemPalace supports AI workflows through MCP tooling, including tools for palace reads and writes, knowledge-graph operations, cross-wing navigation, drawer management, and agent diaries.

OpenViking is an open source context database designed specifically for AI agents, built around a file-system paradigm that unifies the management of memories, resources, and skills. Instead of treating context as scattered chunks in a fragmented vector store, OpenViking organizes agent context into a virtual file system under the viking protocol, giving agents a structured way to store, navigate, retrieve, and observe the information they need. It is designed to help developers move beyond the hassle of manual context management by giving agents a minimalist interaction model for context, similar to reading and writing files. OpenViking supports hierarchical context loading, semantic retrieval, recursive retrieval, sessions, metrics, and observability, making it possible for AI agents to access the right level of information without stuffing everything into the prompt.

Ejentum is a reasoning harness for agentic AI, built as a structured reasoning layer that makes LLM agents more reliable, auditable, and disciplined during long or complex tasks. It works as a tool that an agent can call mid-task, returning the exact cognitive operation matched to the problem in front of it, so the agent can correct reasoning at inference time instead of relying only on static prompts. Ejentum is designed to stop AI agents from drifting, flattering, fabricating, locking into false hypotheses, stopping at shallow answers, or losing important context after several steps. It provides 679 abilities across four cognitive harnesses: reasoning, code, anti-deception, and memory. The reasoning harness channels analytical power across causality, time, space, simulation, abstraction, and metacognition, helping agents avoid surface-level pattern matching.

AgentKey connects your AI agents to the world with one key for the external data they need to do real work. Your agent may know what to do, but to actually do it, they need to find the right API, get the right access, and handle every service. AgentKey handles that layer so the agent can search widely, read pages, pull social takes, and add finance, ecommerce, business, crypto, or on-chain context in one pass. Built for Claude Code, Codex, Cursor, Windsurf, Gemini CLI, OpenClaw, Hermes, Antigravity, Warp, and any platform that supports MCP or Skills files, AgentKey gives agents access to search, scraping, social media, finance, ecommerce, cryptocurrency, and business data without forcing users to juggle separate provider dashboards. Search routes include services like Brave Search, Tavily, Serper, Perplexity, Parallel, and Exa, while scraping routes use tools such as Firecrawl, Jina, and Bright Data to turn web pages into usable content.

Maguyva is agent-first code intelligence that gives AI coding tools a ranked map of a repository before they start editing. Teams connect GitHub repositories, and cloud pipelines parse, rank, and index symbols, dependencies, imports, semantic relationships, and cross-file structure, then keep the index current as code changes. Through one remote MCP integration, agents in Claude Code, Cursor, VS Code, Windsurf, Codex, Gemini CLI, and other compatible clients can query the same grounded context without installing a local indexer or changing editors. Its 11 MCP tools combine semantic, structural, graph, and text retrieval across five search modalities, returning ranked results instead of raw grep output. Agents can ask plain-language questions, locate important symbols, find patterns through AST-aware search, trace dependents, identify orphaned code, analyze a change’s blast radius, and assemble task context before touching a file.

HOL Guard is a local-first runtime security layer for AI agents that watches what an AI assistant is about to do and stops risky actions before they happen. It sits between the agent and the computer, evaluating supported tool calls and local artifacts for threats such as secret and credential exposure, destructive commands, prompt-injection-driven actions, malicious or changed packages, risky MCP configuration, and unsafe plugins, skills, hooks, and settings. Known threats can be blocked automatically, while ambiguous actions are paused for user approval so people remain in control. Guard runs entirely on the developer’s machine, works offline, and does not upload files, prompts, or passwords. Local checks typically complete in under 50 milliseconds and require no changes to existing code or routines. It supports coding agents including Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Hermes, and OpenClaw, with tailored integrations that inspect actions before execution.