Skip to main content
Glama

Antigravity MCP Server

MCP (Model Context Protocol) server for Google Antigravity CLI (agy) integration. Lets any MCP client (Claude Code, Claude Desktop, Cursor, etc.) delegate tasks to Antigravity's agentic CLI — with model selection (Gemini, Claude, GPT-OSS), conversation resume, and workspace controls.

For the why behind it, read the project write-up on trishchuk.com. It covers how I use Claude Code or Cursor as the lead engineer and hand bounded work to Antigravity: long tasks delegated to the Gemini 4 Orchestrator in an isolated git worktree, read-only plans and reviews from a different model family, and large-context digests. It also has a table for choosing the right tool, the costs and isolation limits to know before delegating, and where Google's multi-agent tooling is heading.

Requirements

  • Node.js >= 18

  • Antigravity CLI installed (agy --version works) and authenticated (run agy once interactively and sign in with your Google account)

Related MCP server: antigravity-mcp

Installation

npm install -g @trishchuk/antigravity-mcp-server

додай Or run from source:

pnpm install && pnpm build

MCP client configuration

{
  "mcpServers": {
    "antigravity": {
      "command": "npx",
      "args": ["-y", "@trishchuk/antigravity-mcp-server"],
      "env": {
        "AGY_MCP_CWD": "/path/to/your/project"
      }
    }
  }
}

For Claude Code:

claude mcp add antigravity -- npx -y @trishchuk/antigravity-mcp-server

Tools

Tool

Description

ask-antigravity

Run a prompt through agy in print mode. Supports model + effort, mode, session resume, --add-dir, --sandbox, --dangerously-skip-permissions, dry-run.

plan-antigravity

Generate a structured implementation plan (JSON or markdown) without mutating anything.

review-changes

Collect a git diff (working tree / vs base branch / specific commit) and run a structured code review.

brainstorm

Structured ideation (divergent, convergent, SCAMPER, design-thinking, lateral).

digest-antigravity

Ingest many files/directories and answer a focused question using Antigravity's large model context. Credential files (.env, keys…) are withheld.

batch-antigravity

Run multiple atomic tasks sequentially or in parallel (priority order, stop-on-error, concurrency cap).

bg-antigravity

Detached background tasks: start / status / tail / stop / remove / list. State persists in ~/.agy-mcp/bg/ across server restarts.

delegate-antigravity

Long multi-step tasks: runs detached in its own git worktree, on the Orchestrator model by default; live status, follow-up continue turns, result with the agent report + diff.

list-sessions

List / delete / clear conversation sessions.

list-models

Available models (agy models) grouped by family, with the effort levels each accepts and what it is for.

health

Diagnose CLI installation, authentication, models, and session state.

ping, Help, version, metrics

Utilities.

Background, batch and delegate tools default to --dangerously-skip-permissions because print mode cannot answer interactive permission prompts; pass skipPermissions: false to opt out. An explicit mode turns that default off (the mode is the permission policy), and mode: "plan" with skipPermissions: true is rejected.

Models

The model parameter takes a display label (Gemini 4 Hydrogen (High)), a full ID (gemini-4-hydrogen-high), or a base ID plus effort (model: "gemini-4-hydrogen", effort: "xhigh"). A base label with effort is rejected by the CLI. As of Antigravity CLI v1.5.9 (availability depends on your plan — list-models shows the live list):

Family

Base ID

effort

What it is for

Gemini 4 Hydrogen

gemini-4-hydrogen

low, medium, high, xhigh

Fast everyday coding and maintenance (upgrades, boilerplate, tests, docs). The implementer inside Orchestrator.

Gemini 4 Argon

gemini-4-argon

low, medium, high

Maximum reasoning depth on every step; planner of Orchestrator (Argon).

Gemini 4 Carbon

gemini-4-carbon

low, medium, high

Maximum-depth reasoning (e.g. designing complex systems); planner of Orchestrator (Carbon). Ultra / Enterprise only.

Orchestrator (Argon)

gemini-pro-orchestrator-g1-pro

— (fixed)

Long tasks: the planner plans and reviews, Hydrogen implements, builds and tests, and hands back on repeated failures. One agent, no parallel subagents.

Gemini 3.8 Flash

gemini-3.8-flash

low, medium, high

Claude Opus 5.5

claude-opus-5-5

low, medium, high

Claude Sonnet 5.5

claude-sonnet-5-5

low, medium, high

GPT-OSS 120B

gpt-oss-120b

medium

Scheduled for removal on 2026-11-18.

agy --effort accepts low | medium | high | xhigh | max, but each model supports only the subset above (no current model accepts max); a suffixed ID such as gemini-4-hydrogen-high only accepts its own level. Orchestrator has a fixed thinking level and rejects effort.

Omit model and the server passes no --model flag, so the CLI's own default applies ("model" in ~/.gemini/antigravity-cli/settings.json). The label this server uses in its examples and hints is Gemini 4 Hydrogen (High) — see DEFAULT_MODEL in src/constants.ts.

Delegating long tasks

delegate-antigravity hands a multi-step implementation task to Antigravity and returns immediately:

{
  "task": "Add rate limiting to the /api routes",
  "autoTest": "pnpm test",
  "acceptanceCriteria": ["429 after 100 req/min"]
}
  • Creates a git worktree on a fresh agy/<random> branch under ~/.agy-mcp/delegations/ and runs agy detached there (survives the MCP call and server restarts).

  • Without model, picks the Orchestrator (Carbon if your plan has it, else Argon); otherwise falls back to Gemini 4 Hydrogen (High).

  • Captures --output-format stream-json: action: "status" shows steps, tool calls, the last command and the latest text; action: "continue" with a message sends a follow-up turn into the same conversation and worktree; action: "result" returns the agent's final report, outcome (finished_reason), token usage and the diff against the base commit (cleanup: true removes the worktree and branch).

  • Per-turn timeout defaults to 2 hours (timeout: 0 = none). stop signals the whole process group (signal: SIGTERM by default, SIGKILL for a run that ignores it).

Sessions and conversation resume

ask-antigravity supports multi-turn conversations:

{
  "prompt": "Analyze src/auth.ts for security issues",
  "sessionId": "auth-review"
}
{
  "prompt": "Now suggest fixes for the issues you found",
  "sessionId": "auth-review"
}

How it works: in text output agy doesn't print its conversation ID to stdout, so the server passes --log-file to a temp file and parses the ID from it (Created conversation <uuid> / conversationID="<uuid>"). The next call with the same sessionId resumes via agy --conversation <uuid>.

You can also pass a native conversationId directly, or continueLatest: true for agy --continue.

Session storage is in-memory (lost on server restart). Configure with:

  • AGY_SESSION_TTL_MS — session TTL (default 24h)

  • AGY_MAX_SESSIONS — max stored sessions (default 50)

  • AGY_MCP_CWD — default working directory for agy runs. Resolution order: workingDir → AGY_MCP_CWD → the project root of an @path in your prompt (ask, digest, delegate) → the server's launch directory

Safety

  • skipPermissions: true maps to --dangerously-skip-permissions — agy auto-approves all tool/command permission requests. Use deliberately.

  • sandbox: true maps to --sandbox — terminal restrictions enabled.

  • Since CLI 1.5.7 headless runs start in Auto mode where it is available, which edits files without asking. plan-antigravity, review-changes, digest-antigravity and brainstorm therefore pass --settings '{"agentMode":"","permissions":{"allow":[]}}': Default mode, plus your allow-rules suspended for that run (otherwise a pre-approved command such as git checkout still executes). A headless run cannot answer permission prompts, so writes and shell commands are auto-denied; reading files works and the answer still reaches stdout. (--mode plan is not used because it writes the answer into a plan artifact instead.)

  • mode maps to --mode accept-edits | auto | plan; Auto is not available on every account.

  • A delegation worktree isolates git state, not the filesystem: with skipPermissions (the default for background work) the agent can read and write outside it and run any command.

  • digest-antigravity never sends credential-like files (.env*, .npmrc, private keys, *.pem, …) and does not follow symlinks while walking directories.

  • Cancelling a tool call from the client stops the agy / git processes it started; background and delegated tasks keep running until you stop them.

  • An explicit workingDir / cd that does not exist is an error — the server never falls back to another directory.

  • Otherwise agy uses your configured permission rules (/permissions in interactive agy).

Development

pnpm build          # tsc
pnpm lint           # tsc --noEmit
pnpm test           # build + node --test
pnpm format         # prettier

License

MIT

Available Tools

15 tools
ask-antigravityA
Destructive

Execute Google Antigravity CLI (agy) in print mode with model selection, conversation resume, and workspace controls.

Inputs: prompt (required), cd, mode, model, +12 more.

batch-antigravityB
Destructive

Delegate multiple atomic tasks to Antigravity for batch processing. Ideal for repetitive operations, mass refactoring, and automated transformations.

Inputs: tasks (required), mode, model, effort, +6 more. Returns: total, failed, results, skipped, +1 more

bg-antigravityA
Destructive

Run Antigravity CLI as a detached background task. Subactions: start (returns taskId), status, tail (log output), stop, remove, list. Use for long-running autonomous work — the MCP call returns immediately and you poll status later.

Inputs: action (required), cd, mode, label, +11 more.

brainstormB
Read-only

Generate creative ideas using structured frameworks with domain context and feasibility analysis.

Inputs: prompt (required), cd, model, domain, +6 more.

delegate-antigravityA
Destructive

Delegate a long, multi-step implementation task to Antigravity. Runs detached in its own git worktree/branch, by default on the Orchestrator model (planner + Gemini 4 Hydrogen implementer, built for long tasks). Returns a taskId immediately; poll status for live progress, continue to send follow-up instructions into the same conversation, and result for the final answer + diff. The worktree isolates git state only — with skipPermissions (default) the agent can run any command.

Inputs: mode, task, model, action, +13 more.

digest-antigravityA
Read-only

Ingest many files at once and answer a focused question. Uses Antigravity's large model context (Gemini ~1M tokens) to swallow whole modules / docs that don't fit in the caller's context. Walks directories (symlinks are not followed), filters by extension, withholds credential files (.env, .npmrc, keys…), truncates oversized files, caps total payload. Returns a concentrated brief.

Inputs: paths (required), question (required), model, shape, +8 more.

healthA
Read-onlyIdempotent

Check Antigravity CLI installation, authentication, available models, and session health

Inputs: verbose, sessionId. Returns: agyCli, issues, status, sessions

HelpA
Read-onlyIdempotent

Show Antigravity CLI help output

Inputs: no named parameters.

list-modelsB
Read-onlyIdempotent

List the models available to Antigravity CLI (agy models), grouped by family with the effort levels each accepts and what it is for. Pass a label, a full ID, or a base ID plus effort as the model parameter.

Inputs: no named parameters. Returns: models, families, modelIds

list-sessionsB
Destructive

List active conversation sessions with metadata, or manage them (delete/clear)

Inputs: action, sessionId. Returns: stats, action, sessions

metricsA
Read-onlyIdempotent

Expose Prometheus-formatted metrics for Antigravity MCP server

Inputs: no named parameters.

pingC
Read-onlyIdempotent

Echo

Inputs: prompt.

plan-antigravityA
Read-only

Generate a structured implementation plan using Antigravity. Use BEFORE coding to get steps, files-to-touch, risks, and open questions. Distinct from ask-antigravity: enforces a plan-only system prompt and parses structured output.

Inputs: goal (required), model, effort, format, +5 more.

review-changesB
Read-onlyIdempotent

Run a code review against the current repository using Antigravity (collects git diff + structured review prompt).

Inputs: base, model, title, commit, +5 more.

versionA
Read-onlyIdempotent

Display version and system information

Inputs: no named parameters. Returns: agyCli, nodeJs, platform, mcpServer

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 15 tools

    Disambiguation3/5

    Most tools funnel into the same underlying action (send a prompt to the Antigravity CLI), so ask-antigravity, batch-antigravity, delegate-antigravity, bg-antigravity, plan-antigravity, digest-antigravity, and brainstorm sit on a continuum with fuzzy boundaries. Descriptions do work to differentiate them (plan-only prompt, atomic tasks, detached worktree, directory ingestion), but an agent must read carefully to pick between ask vs delegate vs bg vs batch. The admin tools (health, version, metrics, list-models, ping, Help) are clearly distinct.

    Naming Consistency3/5

    Patterns are readable but mixed: the main delegation family uses verb-antigravity kebab-case, while admin tools use bare nouns (health, metrics, version, ping) and some use verb-noun (review-changes, list-sessions, list-models) or standalone verbs (brainstorm). There is also a case inconsistency ('Help' capitalized while everything else is lowercase). The suffix convention helps group related tools but isn't applied uniformly.

    Tool Count4/5

    15 tools sits at the upper edge of well-scoped, and the split of the core delegation capability into six near-siblings (ask, batch, plan, delegate, bg, digest) inflates the count. Still, each entry maps to a defensible use case and the admin/support tools are lightweight, so the surface is reasonable for a CLI wrapper.

    Completeness4/5

    Coverage is solid for an agent-CLI wrapper: prompt execution, planning, delegation, background task lifecycle (start/status/tail/stop/remove/list), review, document digestion, sessions, model discovery, and health/diagnostics. Gaps are minor: session operations like delete/clear are buried inside list-sessions rather than exposed as their own tools, and there is no explicit cancel for foreground runs.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      C
      maintenance
      Enables MCP-compatible AI clients like Claude Code, Cursor, and Codex to invoke Google Antigravity's Gemini coding agent for repository-aware file operations, command execution, code review, test generation, and quota checks, while also providing a standalone dual-mode CLI.
      7
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables 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.
      1
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables delegating coding tasks to the official Antigravity CLI from any MCP client, with task listing, model selection, streamed event tracking, cancellation, and resumable sessions. Runs each task against an isolated copy of the repository so results can be previewed, tested, and only integrated into the original after explicit user confirmation.
      23
      34 npm
      MIT