agent-antigravity-mcp
This server provides an MCP interface to the Google Gemini Antigravity Agent for autonomous code execution, web browsing, and more. You can:
Manage agent interactions: create, continue, cancel, list, and poll status; submit custom function results; process text and base64 image inputs; run asynchronously with token budgets.
Execute code remotely: run shell, Python, and Node.js commands in Linux sandboxes; manage sandbox environments (create, list, inspect, delete, upload/download files, snapshot as .tar).
Browse the web: integrated
google_searchandurl_contexttools.Schedule cron triggers: create, list, pause/resume, delete, run on demand, and audit execution history for recurring interactions.
Automate GitHub PRs: clone a repo, branch, complete a task, push, and open a PR with secure token injection via network allowlist.
Register managed agents: reusable named agents with persistent system instructions, default tools, and base environments.
Configure extensibility: connect external MCP servers, set pre/post hooks for tool interception, build environment configs with file sources and network rules.
Choose Gemini models like
gemini-3.6-flashandgemini-3.5-flash-lite.Reliable operation: API call fallbacks with exponential backoff and interaction session caching.
Enables GitHub Pull Request workflow: branching, committing, pushing changes, and opening PRs from a task description, with token injection via sandbox network allowlist.
Provides tools to create, manage, and continue interactions with Google Gemini Antigravity Agent, including autonomous code execution, web browsing, multimodal inputs, and function calling.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-antigravity-mcpcreate a GitHub PR to update the README with installation instructions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Agent Antigravity MCP Server
Model Context Protocol (MCP) server for Google Gemini Antigravity Agent.
Features
Autonomous Code Execution: Run shell, Python, Node.js commands in remote Linux sandbox.
Web Browsing & Search: Integrated
google_searchandurl_context.Multimodal Inputs: Process text instructions and base64 images.
Custom Functions: Support turn-based custom function calling.
Remote MCP Servers: Connect external MCP servers to Antigravity agent.
Model Selection: Choose between
gemini-3.6-flash,gemini-3.5-flash-lite, and other Gemini models.Background Execution: Async interactions with
background=Truepolling andmax_total_tokensbudget cap.Environment Config: Build remote sandbox config with file sources (inline/git/gcs) and network allowlist.
Cron Triggers: Create, list, pause/resume, delete, run, and audit scheduled recurring interactions.
GitHub PR Workflow: Point at a repo (public/private) + base branch; agent branches, does the task, pushes, opens the PR. Token injected via sandbox network allowlist, never in the prompt.
Managed Agents: Register reusable named agents (
system_instruction, default tools,base_environment) and invoke them by ID.Environments API: List/inspect/delete sandbox environments directly, and download a sandbox's full filesystem as a
.tar.Hooks Config: Mount a
hooks.json(pre/postcode_execution/file-op interception, allow/deny) into the sandbox via an inline environment source — format documented increate_interaction'senvironmentarg.
Related MCP server: gpal
Tools
Tool | Covers |
| Interactions API create + multi-turn + function calling + |
| Interaction status, polling, cancel, delete |
| Triggers API (cron scheduling) |
| Clone repo, branch, do task, push, open PR |
| Managed Agents API (register + invoke by ID) |
| Environments API (sandbox lifecycle + file transfer) |
Note: the Interactions API supports stream=true for real-time step deltas via the
google-genai SDK directly (AntigravityClient.create_interaction(..., stream=True)),
but it's not exposed as an MCP tool — MCP tool calls are synchronous request/response,
so there's no way to surface incremental deltas over this transport.
Installation
Clone it somewhere and note the full path:
git clone https://github.com/bgembalczyk/agent-antigravity-mcp.git
cd agent-antigravity-mcp && pwdEvery client below runs the server the same way — uv run --project <that path> agent-antigravity over stdio — so you need
uv installed, but no manual venv or pip install step. In every snippet, replace PATH_TO_REPO with the pwd
output above (full path, not ~).
Claude Code (as a plugin, recommended)
No local clone needed — Claude Code clones it straight from GitHub:
/plugin marketplace add bgembalczyk/agent-antigravity-mcp
/plugin install agent-antigravity@agent-antigravity-mcpExport GEMINI_API_KEY/GITHUB_TOKEN in your shell profile before launching
Claude Code — the plugin's .mcp.json reads them via ${GEMINI_API_KEY}/${GITHUB_TOKEN}.
Antigravity CLI / IDE
File: ~/.gemini/config/mcp_config.json
"agent-antigravity": {
"command": "uv",
"args": ["run", "--project", "PATH_TO_REPO", "agent-antigravity"],
"env": { "GEMINI_API_KEY": "${GEMINI_API_KEY}", "GITHUB_TOKEN": "${GITHUB_TOKEN}" }
}Paste that inside the top-level "mcpServers": { ... } object (create it with
just {"mcpServers": {}} if the file doesn't exist yet).
Codex CLI
File: ~/.codex/config.toml
[mcp_servers.agent-antigravity]
command = "uv"
args = ["run", "--project", "PATH_TO_REPO", "agent-antigravity"]
[mcp_servers.agent-antigravity.env]
GEMINI_API_KEY = "your_gemini_api_key"
GITHUB_TOKEN = "your_github_pat_with_repo_scope"Append that to the end of the file — TOML tables don't care what's above them. Codex doesn't expand shell vars here, so put the real key values in.
GitHub Copilot CLI
File: ~/.copilot/mcp-config.json
"agent-antigravity": {
"type": "local",
"command": "uv",
"args": ["run", "--project", "PATH_TO_REPO", "agent-antigravity"],
"env": { "GEMINI_API_KEY": "your_gemini_api_key", "GITHUB_TOKEN": "your_github_pat_with_repo_scope" },
"tools": ["*"]
}Paste inside "mcpServers": { ... } (create the file with {"mcpServers": {}}
if needed). Takes effect immediately, no restart. Same as Codex, real values
in env — Copilot CLI doesn't expand shell vars here either.
OpenCode
File: ~/.config/opencode/.opencode.json (global) or opencode.json in a
project root (project-scoped).
"agent-antigravity": {
"type": "local",
"command": ["uv", "run", "--project", "PATH_TO_REPO", "agent-antigravity"],
"environment": { "GEMINI_API_KEY": "{env:GEMINI_API_KEY}", "GITHUB_TOKEN": "{env:GITHUB_TOKEN}" }
}Paste inside "mcp": { ... } (create with {"mcp": {}} if needed).
{env:VAR_NAME} expands from your shell environment at startup. Restart
OpenCode (or reload config) after saving.
Any other MCP client / standalone
Any client that speaks MCP over stdio can launch this server the same way:
uv run --project PATH_TO_REPO agent-antigravity. If you'd rather manage the
virtualenv yourself instead of letting uv run do it:
uv venv --clear venv
uv pip install -e .
venv/bin/agent-antigravityConfiguration
Create .env file:
GEMINI_API_KEY=your_gemini_api_key
GITHUB_TOKEN=your_github_pat_with_repo_scopeGITHUB_TOKEN fallback used by create_github_pr_task when no github_token param given. Needs repo scope for private repos.
Optional:
AGENT_ANTIGRAVITY_LOG_LEVEL=INFO
AGENT_ANTIGRAVITY_SESSIONS_DB=/custom/path/sessions.db
AGENT_ANTIGRAVITY_TRANSPORT=stdio # stdio | sse | streamable-http
AGENT_ANTIGRAVITY_HOST=127.0.0.1 # sse/streamable-http only
AGENT_ANTIGRAVITY_PORT=8000 # sse/streamable-http only
AGENT_ANTIGRAVITY_MAX_REQUESTS_PER_MINUTE=60 # 0 disables limitingUsage
Once registered with any client above, the server starts automatically over
stdio whenever that client launches — nothing to run manually. In Claude Code,
the agent-antigravity skill (skills/agent-antigravity/SKILL.md) also
auto-activates when a task matches, on top of the raw MCP tools being available.
Reliability
Every API call tries the
google-genaiSDK first, falls back to direct REST on failure (logged at WARNING). REST calls retry on429/5xx/transport errors with exponential backoff (3 attempts).Interaction session cache is SQLite-backed (
~/.agent-antigravity/sessions.dbby default) and survives process restarts.CI (
.github/workflows/test.yml) runs the test suite on every push/PR.
Testing
uv pip install -e ".[dev]"
pytest -qCredit
Structure and tool/resource/prompt patterns inspired by jules-mcp-server, an MCP server for Google Jules.
License
MIT — see LICENSE.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityCmaintenanceA lightweight MCP server bridging AI agents to Google's Gemini AI via official CLILast updated392MIT
- AlicenseAqualityCmaintenanceAn MCP server that gives your IDE or agent access to Google Gemini with autonomous codebase exploration, enabling deep code analysis, architectural reviews, and bug hunting.Last updated2010MIT
- AlicenseAqualityCmaintenanceAn advanced MCP server that provides an agentic interface to Google's Gemini 3.1 models via Vertex AI, combining real-time Google Search, URL analysis, and Python code execution to solve complex multi-step research and data tasks.Last updated1MIT
- AlicenseAqualityAmaintenanceAn MCP server that bridges Claude Code with Antigravity CLI using a Swarm Agent architecture to optimize local development workflows and minimize LLM token costs. Includes a web UI for monitoring agent workflows.Last updated1516MIT
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bgembalczyk/agent-antigravity-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server