ask-antigravity
Execute Google Antigravity CLI (agy) in print mode with model selection, conversation resume, and workspace controls.
cdmodemodeldryRuneffortpromptrequiredaddDirssandboxtimeoutsessionIdworkingDirresetSession+4 more
io.github.x51xxxPublished by GitHub account x51xxxv0.3.0Updated Nov 14, 2026
Hand work from Claude Code or Cursor to Google Antigravity CLI: delegation, reviews, digests
Bridges MCP clients like Claude Code or Cursor to Google Antigravity CLI, letting an assistant delegate prompts, plans, reviews and long coding tasks to other…
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
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.
agy --version works) and authenticated (run agy once interactively and sign in with your Google account)додай Or run from source:
For Claude Code:
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.
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):
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.
delegate-antigravity hands a multi-step implementation task to Antigravity and returns immediately:
agy/<random> branch under ~/.agy-mcp/delegations/ and runs agy detached there (survives the MCP call and server restarts).model, picks the Orchestrator (Carbon if your plan has it, else Argon); otherwise falls back to Gemini 4 Hydrogen (High).--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).timeout: 0 = none). stop signals the whole process group (signal: SIGTERM by default, SIGKILL for a run that ignores it).ask-antigravity supports multi-turn conversations:
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 directoryskipPermissions: true maps to --dangerously-skip-permissions — agy auto-approves all tool/command permission requests. Use deliberately.sandbox: true maps to --sandbox — terminal restrictions enabled.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.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.agy / git processes it started; background and delegated tasks keep running until you stop them.workingDir / cd that does not exist is an error — the server never falls back to another directory./permissions in interactive agy).MIT
Source: README.md at commit 2eefe25
Execute Google Antigravity CLI (agy) in print mode with model selection, conversation resume, and workspace controls.
cdmodemodeldryRuneffortpromptrequiredaddDirssandboxtimeoutsessionIdworkingDirresetSession+4 moreDelegate multiple atomic tasks to Antigravity for batch processing. Ideal for repetitive operations, mass refactoring, and automated transformations.
modemodeltasksrequiredefforttimeoutparallelworkingDirconcurrencystopOnErrorskipPermissionsRun a code review against the current repository using Antigravity (collects git diff + structured review prompt).
basemodeltitlecommiteffortprompttimeoutworkingDiruncommittedGenerate 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.
goalrequiredmodeleffortformattimeoutacceptanceworkingDirconstraintscontextFilesGenerate creative ideas using structured frameworks with domain context and feasibility analysis.
cdmodeldomaineffortpromptrequiredideaCountconstraintsmethodologyexistingContextincludeAnalysisRun 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.
cdmodelabellinesmodelactionrequiredeffortpromptsignaltaskIdaddDirssandbox+3 moreIngest 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.
modelpathsrequiredshapeeffortexcludetimeoutquestionrequiredrecursiveextensionsworkingDirmaxTotalBytesmaxBytesPerFileDelegate 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.
modetaskmodelactioneffortsignaltaskIdcleanupmessagesandboxtimeoutautoTest+5 moreList active conversation sessions with metadata, or manage them (delete/clear)
actionsessionIdCheck Antigravity CLI installation, authentication, available models, and session health
verbosesessionIdList 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.
Takes no parameters.
Echo
promptShow Antigravity CLI help output
Takes no parameters.
Display version and system information
Takes no parameters.
Expose Prometheus-formatted metrics for Antigravity MCP server
Takes no parameters.
90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
npm install -g @trishchuk/antigravity-mcp-serverpnpm install && pnpm build{ "mcpServers": { "antigravity": { "command": "npx", "args": ["-y", "@trishchuk/antigravity-mcp-server"], "env": { "AGY_MCP_CWD": "/path/to/your/project" } } }}claude mcp add antigravity -- npx -y @trishchuk/antigravity-mcp-server{ "task": "Add rate limiting to the /api routes", "autoTest": "pnpm test", "acceptanceCriteria": ["429 after 100 req/min"]}{ "prompt": "Analyze src/auth.ts for security issues", "sessionId": "auth-review"}{ "prompt": "Now suggest fixes for the issues you found", "sessionId": "auth-review"}pnpm build # tscpnpm lint # tsc --noEmitpnpm test # build + node --testpnpm format # prettier