antigravity-mcp
Click on "Deploy 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., "@antigravity-mcp dispatch a Gemini agent to add tests for the parser"
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.
antigravity-mcp-fork
A fork of Kio-pon/antigravity-mcp that adds GPT-planned native multi-parent orchestration, local job supervision, and signed job-event webhooks on top of the upstream Antigravity IDE bridge.
Upstream exposes 6 tools. This fork exposes 8 — the same 6 plus
get_agent_job_status and supervise_agent_job.
Provenance
This is a downstream fork, not an independent project.
Upstream | |
Upstream base commit |
|
Upstream license | MIT, Copyright (c) 2026 Kio-pon |
Local version |
|
Five of the nine upstream modules are byte-identical to the base commit:
__init__.py, __main__.py, discovery.py, paths.py, protocol.py.
Four were modified to wire in the added features:
Module | Upstream lines changed | What changed |
| ~536 | Native tree tracking; rewrote context-size truncation |
| ~201 | Registers the two added tools; hooks |
| ~209 |
|
| ~100 |
|
The local version string was bumped to 1.1.0.post1 specifically so this fork can
never be confused with upstream 1.1.0 — both previously reported 1.1.0 while
behaving differently, which made them indistinguishable from a client's point of view.
Related MCP server: Antigravity MCP Bridge
Added modules
These eight modules do not exist upstream:
Module | Lines | Responsibility |
| 382 | Tracks only native descendant trees created by a validated GPT plan |
| 302 | MCP job-attention subscriptions; signed, durable webhook delivery |
| 250 | Non-LLM 300-second supervision of registered jobs ( |
| 210 | Runs independent native root trees against one pinned local IDE endpoint |
| 153 | Validates a parent's final report against the observed conversation tree |
| 119 | Validates GPT plans before any native worker tree is created |
| 102 | Validates independent multi-parent plans; requires sibling writes to be disjoint |
| 89 | Loads persistent collaboration preferences |
Tools
Tool | Source |
| upstream |
| upstream |
| upstream |
| upstream |
| upstream |
| upstream |
| this fork |
| this fork |
Execution model
The intended loop: GPT plans and reviews; Gemini executes.
workflow_settings.json (shipped alongside the package) pins the policy:
{
"default_model": "Gemini 3.8 Flash (High)",
"planner": "gpt",
"mode": "native_multi_parent",
"min_workers_per_parent": 2,
"min_agents_per_worker": 2,
"single_parent_conversation": false,
"same_ide": true,
"subagent_model": "inherit",
"independent_tasks_required": true,
"require_all_terminal_results": true
}Backends are tried in order: the local Antigravity language server, then the Gemini REST API. If neither is reachable the job fails with an explicit error — there is deliberately no fallback tier that returns an invented result.
Install
Requires Python 3.9+. Zero runtime dependencies (standard library only).
pip install -e .Run over stdio:
python -m antigravity_mcpMCP client configuration:
{
"mcpServers": {
"antigravity-mcp": {
"command": "python",
"args": ["-m", "antigravity_mcp"],
"env": { "PYTHONPATH": "D:\\path\\to\\antigravity-mcp-fork\\src" }
}
}
}Environment variables
Variable | Default | Purpose |
| platform state dir | Where |
|
| Jobs running at once; extras queue |
|
| Tool calls handled in parallel |
|
| Seconds before a job is abandoned |
| unset | Skip the local backend entirely |
| unset | Selects the job-event/webhook profile |
|
| Log verbosity (written to stderr) |
Shared state warning
paths.py resolves the state directory to %LOCALAPPDATA%\antigravity-mcp on Windows
(and the equivalent per-platform location elsewhere). Upstream antigravity-mcp
resolves to the same directory.
If you install both, they share one jobs.json. This fork writes extra
native_forest* metadata keys that upstream ignores, and upstream writes records
lacking those keys. Neither crashes today, but it is shared mutable state between
two different codebases. If you run both, pin a separate directory for each:
set ANTIGRAVITY_STATE_DIR=%LOCALAPPDATA%\antigravity-mcp-forkStatus
Verified on Windows x64 with Python 3.12: the server starts from the fork's own
src/tree, completes the MCP handshake, and lists all 8 tools.Upstream notes that only Linux has been verified on real hardware against Antigravity IDE v1.107.0.
No automated test suite is included in this repository yet; upstream's
tests/directory was not carried over because the fork's modified modules diverge from it.
License
MIT. Original work Copyright (c) 2026 Kio-pon, see LICENSE.
Fork modifications are distributed under the same MIT terms.
Available Tools
8 toolscancel_agent_jobB
Cancel a running background subagent job.
Inputs: job_id (required).
check_agent_jobB
Check the status, logs, duration, and output of a dispatched agent job.
Inputs: job_id (required).
dispatch_gemini_agentA
Dispatch a coding, analysis, or research task to a background Antigravity subagent. Returns immediately with a job_id so the orchestrator is never blocked.
Inputs: task (required), model, context_files, system_instruction.
gemini_code_searchB
Use a large-context model to scan multiple repository files at once and answer architectural or code questions about them. Runs synchronously and returns the answer.
Inputs: query (required), context_files (required), model.
get_agent_job_statusA
Read compact status for one known job_id without task prompts, logs or full output. Prefer for low-token follow-up.
Inputs: job_id (required).
list_active_jobsC
List active, pending, completed, cancelled, or failed subagent jobs.
Inputs: limit.
list_available_modelsA
List the live models available from the Antigravity IDE or Gemini REST fallback. Call this before dispatch_gemini_agent when you do not already know an exact, currently-live model name.
Inputs: no named parameters.
supervise_agent_jobA
Enable/disable local non-LLM 300-second supervision of one known job. Does not itself schedule or wake GPT. Native dispatches enable it automatically. Acknowledge a stall only after reviewing it.
Inputs: job_id (required), enabled, acknowledge.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Most tools have clearly distinct purposes (dispatch, cancel, list, supervise, model listing, synchronous code search). The one genuinely confusable pair is check_agent_job vs get_agent_job_status, which both read job status, but the descriptions draw a useful line between full logs/output versus compact low-token status.
Seven of eight tools follow a clear verb_noun pattern (list_available_models, check_agent_job, cancel_agent_job, get_agent_job_status, etc.). The single outlier, gemini_code_search, is noun-first and breaks the convention, but overall the set is predictable.
Eight tools is well-scoped for a dispatch-and-monitor server, with each tool covering a distinct lifecycle step (discover models, dispatch, poll, cancel, supervise, list, code search). Nothing feels redundant or missing at the count level.
The surface covers the full lifecycle of dispatching, monitoring, supervising, and cancelling background jobs, plus model discovery and synchronous code search. Minor gaps exist around job cleanup/retention and retry/resume of failed jobs, which agents can work around.
Maintenance
Related MCP Connectors
Public MCP for agent verification, work discovery and governed interoperability.
- aXDeprecatedio.github.ax-platform
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Related MCP Servers
- AlicenseBqualityBmaintenanceAn MCP bridge that lets Codex delegate long-running agent work to the Antigravity CLI, providing observable and resumable tool-based execution with project scoping.1439 PyPI17MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI clients to run Google Antigravity coding sub-agents as MCP tools, with synchronous and asynchronous execution, task polling, and sandboxed Docker workspace isolation.-
- AlicenseAqualityBmaintenanceEnables MCP clients such as Claude Code, Codex, and Cursor to dispatch background subagent jobs to the Antigravity IDE's local agent engine and collect results asynchronously. Jobs run through the IDE's authenticated session without an API key, with optional Gemini REST fallback and on-disk job history.62MIT
- AlicenseAqualityCmaintenanceEnables MCP clients to delegate background subagent jobs to an IDE's local agent engine, queue and monitor them, and retrieve results while the orchestrator continues working.7MIT