MetaGravity
Orchestrates Google Antigravity agent sessions and CLI chats, enabling launching, steering, archiving, listing, and reading transcripts of Antigravity conversations.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
🚀 MetaGravity (metagravity-mcp)
MetaGravity is a Model Context Protocol (MCP) Server and Python SDK for orchestrating Google Antigravity agents and CLI sessions. Inspired by T3 Code's autonomous multi-chat spawning, MetaGravity enables one lead chat or script to spawn, steer, and archive multiple child agent sessions across GitHub issues or feature folders.
💡 Why MetaGravity?
In harnesses like T3 Code, an agent can effortlessly say:
"Open 3 parallel chats in this repo, one for each of these 3 GitHub issues, execute them in background, and give them initial prompts."
Antigravity natively supports reading and continuing threads via agy, but lacked an effortless, standardized MCP interface for programmatic multi-chat dispatch. MetaGravity bridges that gap.
Core Primitives
launch_chat: Spawns a dedicated Antigravity session in target project folderX, with configurable permissions (turbo/--dangerously-skip-permissions,auto,plan), and an initial trigger prompt.add_comment: Injects follow-up prompts or answers interactive choices (e.g., auto-selecting option4when a session is paused waiting for user confirmation).archive_chat: Formally archives / tombstones completed conversations in Antigravity's metadata (annotations/<cid>.pbtxt) so active monitoring stays clean.list_chats: Discovers active and past threads directly from Antigravity's internal SQLite database (conversation_summaries.db).get_transcript: Reads step-by-step logs and tool outputs from Antigravity's brain transcript.
Related MCP server: switchboard
🛠️ Quickstart
1. Installation
git clone https://github.com/palladius/metagravity-mcp.git
cd metagravity-mcp
pip install -e .Or run directly with uv:
uv run --project . metagravity mcp2. Configure with your MCP Client (Claude Desktop, Cursor, Hermes, T3)
Add to your claude_desktop_config.json or MCP settings:
{
"mcpServers": {
"metagravity": {
"command": "python3",
"args": ["-m", "metagravity.server"],
"cwd": "/path/to/metagravity-mcp"
}
}
}🧰 Available MCP Tools
Tool | Parameters | Description |
|
| Spawns a new Antigravity agent in the project directory. |
|
| Appends a comment or resolves a 1-2-3-4 selection prompt. |
|
| Tombstones and archives a conversation. |
|
| Lists active/past threads with status and step count. |
|
| Inspects recent tool calls and steps from the agent's brain. |
💻 CLI Usage
MetaGravity also doubles as a standalone command-line manager:
# List active chats
metagravity list --open
# Launch a new autonomous chat on a GitHub issue
metagravity launch --project ~/git/my-repo --prompt "Fix issue #12: add healthcheck endpoint" --turbo
# Answer option 4 on a waiting chat
metagravity comment 96b7e2e7 --choice 4
# Archive a finished conversation
metagravity archive 96b7e2e7🐍 Python SDK Example
from metagravity import MetaGravityClient
client = MetaGravityClient()
# Launch 3 parallel agent chats for 3 GitHub issues
issues = [
(101, "Fix memory leak in cache poller"),
(102, "Add dark mode toggle to UI"),
(103, "Update integration test suite"),
]
sessions = []
for issue_id, title in issues:
res = client.launch_chat(
project="/Users/riccardo/git/my-project",
prompt=f"Please solve GitHub Issue #{issue_id}: {title}. Run tests when done.",
turbo=True,
background=True,
)
print(f"Spawned Issue #{issue_id} -> PID: {res['pid']}")
sessions.append(res)📄 License
Apache-2.0 - Built with 💛 by Riccardo Carlesso & Ermete Bottazzi.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Command center for developers coordinating AI coding agents across projects.
Sync coding-agent sessions and resume them in any other agent: Claude Code, Codex, Cursor, more.
Project memory, documentation and controlled secret access for AI coding agents.
Operate hilos project rooms, Docs, Tasks, messages, memory, and coding-agent review workflows.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides a local chat room for coordinating work across Git worktrees, coding agents (Claude, Codex), and humans, with tools to start, wake, stop, message, and search agent sessions.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceCoordinates parallel Claude Code agents on shared repositories and orchestrates multiple Claude subscriptions, enabling live session handoff, conflict detection, and remote terminal control.8 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables multiple AI coding CLIs (Claude Code, Gemini/Antigravity, Codex, and OpenCode) to collaborate as a coordinated team by routing cross-agent prompts, sharing messages and review tickets, tracking tasks on a shared store, and isolating each agent in its own Git worktree with turn-budget safeguards—all inspectable and steerable from a local web dashboard.MIT
- AlicenseNot gradedqualityBmaintenanceEnables Codex users to delegate engineering, refactoring, auditing, and test execution tasks to Google Antigravity CLI as a persistent autonomous subagent, with tools for managing sessions and running prompts.1MIT