Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Antigravity MCP Server

NPM · @TRISHCHUK/ANTIGRAVITY-MCP-SERVER

Hand work from Claude Code or Cursor to Google Antigravity CLI: delegation, reviews, digests

+18 this week 66 Trust /100

Last scanned (16 hours ago)

Scores higher than 38% of npm servers

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security80
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability70
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3878 tokens (~258/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
  • 93% of tools have a non-trivial description (not blank, and not just the tool's name).Partial
  • 93% of tool parameters carry a description.Partial
  • Structured output schemas are declared (33% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes. Other categories moved too: Supply Chain Security fell 1.

  • 17 Nov 26 +2
    • Stability: unverified → 0.10 ▲ functional
  • 15 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 14 Nov 26 48

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/@trishchuk/antigravity-mcp-server@0.3.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 93 packages
Packages resolved 93
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 15 exposed · ~3,878 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ask-antigravity ~583

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

NameTypeReqDescription
addDirsarray–Additional workspace directories (--add-dir, repeatable).
cdstring–Working directory
continueLatestboolean–Use --continue to resume the most recent conversation.
conversationIdstring–Native Antigravity conversation ID to resume (--conversation). Overrides sessionId lookup.
dryRunboolean–Return the resolved CLI argv as JSON without spawning agy.
effortstring–Reasoning effort (--effort). Supported levels depend on the model — see list-models. Use with a base model ID (e.g. gemini-4-hydrogen); not supported by Orchestrator.
modestring–Agent mode (--mode): accept-edits, auto (sandboxed autonomy; not available on every account), or plan (answers go into a plan artifact).
modelstring–Optional model override (ID or display label from `agy models`). Known: Gemini 4 Hydrogen (Low), Gemini 4 Hydrogen (Medium), Gemini 4 Hydrogen (High), Gemini 4 Hydrogen (XHigh), Gemini 4 Argon (Low),…
promptstringyesTask or question. Reference files by path — agy reads them with its own tools.
resetSessionboolean–Clear session context before execution. Starts fresh conversation.
responseModestring–Response verbosity: "clean" returns only the final answer (default), "full" includes the stderr execution log.
sandboxboolean–--sandbox: run with terminal restrictions enabled.
sessionIdstring–Internal session ID for conversation continuity (workspace-isolated).
skipPermissionsboolean–⚠️ --dangerously-skip-permissions: auto-approve all tool permission requests.
timeoutinteger–Maximum execution time in milliseconds (default 600000)
workingDirstring–Working directory for execution (alias of cd)

No output schema declared.

No examples provided.

batch-antigravity ~454

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

NameTypeReqDescription
concurrencyinteger–Maximum parallel agy processes when parallel=true. Default: min(task count, 4)
effortstring–Reasoning effort (--effort). Supported levels depend on the model — see list-models. Use with a base model ID (e.g. gemini-4-hydrogen); not supported by Orchestrator.
modestring–Agent mode (--mode): accept-edits, auto (sandboxed autonomy; not available on every account), or plan (answers go into a plan artifact).
modelstring–Optional model override applied to every task. Known: Gemini 4 Hydrogen (Low), Gemini 4 Hydrogen (Medium), Gemini 4 Hydrogen (High), Gemini 4 Hydrogen (XHigh), Gemini 4 Argon (Low), Gemini 4 Argon (M…
parallelboolean–Execute independent tasks in parallel
skipPermissionsboolean–--dangerously-skip-permissions. Default: true (print mode can't answer prompts), false when `mode` is set. Not allowed with mode plan.
stopOnErrorboolean–Stop execution if any task fails
tasksarrayyesArray of atomic tasks to delegate to Antigravity
timeoutinteger–Maximum execution time per task in milliseconds
workingDirstring–Working directory for execution
NameTypeReqDescription
failednumberyes–
resultsarrayyes–
skippednumberyes–
successfulnumberyes–
totalnumberyes–

No examples provided.

bg-antigravity ~543

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.

NameTypeReqDescription
actionstringyesBackground task action.
addDirsarray––
cdstring––
effortstring–Reasoning effort (--effort). Supported levels depend on the model — see list-models. Use with a base model ID (e.g. gemini-4-hydrogen); not supported by Orchestrator.
labelstring–Human-readable label to identify this task later.
linesinteger–Lines to return from log tail.
modestring–Agent mode (--mode): accept-edits, auto (sandboxed autonomy; not available on every account), or plan (answers go into a plan artifact).
modelstring–Optional model override. Known: Gemini 4 Hydrogen (Low), Gemini 4 Hydrogen (Medium), Gemini 4 Hydrogen (High), Gemini 4 Hydrogen (XHigh), Gemini 4 Argon (Low), Gemini 4 Argon (Medium), Gemini 4 Argon…
promptstring–Prompt (required for action=start).
sandboxboolean–--sandbox: run with terminal restrictions enabled.
signalstring–Signal for action=stop (default SIGTERM; SIGKILL for a run that ignores it).
skipPermissionsboolean–--dangerously-skip-permissions. Default: true (print mode can't answer permission prompts), false when `mode` is set. Not allowed with mode plan.
taskIdstring–Task ID returned by action=start.
timeoutnumber–agy --print-timeout in milliseconds. Omit for no limit (agy waits for the turn and its background tasks).
workingDirstring––

No output schema declared.

No examples provided.

brainstorm ~413

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

NameTypeReqDescription
cdstring–Working directory
constraintsstring–Limitations: budget, time, technical, legal, etc.
domainstring–Domain: software, business, creative, research, product, marketing, etc.
effortstring–Reasoning effort (--effort). Supported levels depend on the model — see list-models. Use with a base model ID (e.g. gemini-4-hydrogen); not supported by Orchestrator.
existingContextstring–Background info or previous attempts
ideaCountinteger–Number of ideas (default: 12, range: 5-30)
includeAnalysisboolean–Include feasibility/impact analysis
methodologystring–Framework: divergent, convergent, scamper, design-thinking, lateral, auto (default)
modelstring–Optional model override. Known: Gemini 4 Hydrogen (Low), Gemini 4 Hydrogen (Medium), Gemini 4 Hydrogen (High), Gemini 4 Hydrogen (XHigh), Gemini 4 Argon (Low), Gemini 4 Argon (Medium), Gemini 4 Argon…
promptstringyesBrainstorming challenge or question

No output schema declared.

No examples provided.

delegate-antigravity ~600

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.

NameTypeReqDescription
acceptanceCriteriaarray–Bullet list of criteria the implementation must satisfy.
actionstring–start: spawn a delegated task; status: live progress; continue: send a follow-up turn to the same conversation; result (alias collect): final answer + diff; stop: kill the running turn; list: all del…
autoTeststring–Command the agent must run to verify its work (e.g. "npm test"); it is told to loop until it passes.
baseBranchstring–Branch/commit to base the worktree on (default: current HEAD of repo).
branchNamestring–Name for the new branch in the worktree. Default: agy/<random>.
cleanupboolean–On result/collect: also remove the worktree and delete the branch after grabbing the diff.
effortstring–--effort for non-Orchestrator models (Orchestrator has a fixed thinking level).
messagestring–Follow-up instruction for action=continue.
modestring–Agent mode (--mode): accept-edits, auto (sandboxed autonomy; not available on every account), or plan (answers go into a plan artifact).
modelstring–Model ID or label. Omit to use the Orchestrator (Carbon, else Argon) when your plan has one, otherwise Gemini 4 Hydrogen (High).
sandboxboolean–--sandbox: run terminal commands in the OS sandbox.
signalstring–Signal for action=stop (default SIGTERM; SIGKILL for a run that ignores it).
skipPermissionsboolean–--dangerously-skip-permissions (default true: a headless run cannot answer permission prompts; false when `mode` is set; not allowed with mode plan). The worktree isolates git state, NOT the filesyst…
taskstring–What Antigravity should accomplish (required for start).
taskIdstring–Delegation ID returned by start (any turn's task ID also works).
timeoutinteger–Per-turn --print-timeout in milliseconds (default 7200000 = 2h; 0 = no limit).
workingDirstring–Repo root (default: resolved automatically).

No output schema declared.

No examples provided.

digest-antigravity ~411

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.

NameTypeReqDescription
effortstring–Reasoning effort (--effort). Supported levels depend on the model — see list-models. Use with a base model ID (e.g. gemini-4-hydrogen); not supported by Orchestrator.
excludearray–Substrings to exclude from paths (matched against relative path). Default: node_modules, .git, dist, build.
extensionsarray–Filter by extensions when walking dirs (e.g., [".ts", ".tsx"]). Default: all text-like files.
maxBytesPerFileinteger–Truncate any single file above this size. Default: 200 KB.
maxTotalBytesinteger–Stop adding files once the total payload exceeds this. Gemini models have ~1M-token contexts; 8 MB default leaves headroom.
modelstring––
pathsarrayyesFiles or directories to ingest, inside workingDir (symlinks are resolved; anything outside is skipped). Directories are walked. Globs are NOT expanded — pass concrete paths.
questionstringyesFocused question to answer using the provided files (e.g., "explain auth flow", "find dead code").
recursiveboolean–Walk into subdirectories. Default: true.
shapestring–summary: 1-paragraph; detailed: structured deep-dive; qa: focused answer to the question.
timeoutinteger–Maximum execution time in milliseconds (default 600000)
workingDirstring––

No output schema declared.

No examples provided.

health ~50

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

NameTypeReqDescription
sessionIdstring–Optional session ID to check specific session health
verboseboolean–Include detailed diagnostic information
NameTypeReqDescription
agyCliobjectyes–
issuesarrayyes–
sessionsobjectyes–
statusstringyes–

No examples provided.

Help ~15

Show Antigravity CLI help output

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list-models ~65

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.

Input schema present but exposes no named parameters.

NameTypeReqDescription
familiesarray––
modelIdsarray––
modelsarrayyes–

No examples provided.

list-sessions ~59

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

NameTypeReqDescription
actionstring–Action: list (default), delete (single session), clear (all sessions)
sessionIdstring–Session ID for delete action
NameTypeReqDescription
actionstringyes–
sessionsarray––
statsobject––

No examples provided.

metrics ~21

Expose Prometheus-formatted metrics for Antigravity MCP server

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ping ~19

Echo

NameTypeReqDescription
promptstring–Message to echo

No output schema declared.

No examples provided.

plan-antigravity ~231

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.

NameTypeReqDescription
acceptancearray–Acceptance criteria the plan must satisfy.
constraintsstring–Hard constraints (must-not-touch areas, style rules, deadlines).
contextFilesarray–Paths/globs to reference in the prompt.
effortstring–Reasoning effort (--effort). Supported levels depend on the model — see list-models. Use with a base model ID (e.g. gemini-4-hydrogen); not supported by Orchestrator.
formatstring–Output shape. json (default) returns structured steps/risks; markdown returns a checklist.
goalstringyesWhat you want planned (a feature, refactor, investigation).
modelstring––
timeoutinteger–Maximum execution time in milliseconds (default 600000)
workingDirstring––

No output schema declared.

No examples provided.

review-changes ~401

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

NameTypeReqDescription
basestring–Review changes against a specific base branch (e.g., "main", "develop")
commitstring–Review changes introduced by a specific commit SHA
effortstring–Reasoning effort (--effort). Supported levels depend on the model — see list-models. Use with a base model ID (e.g. gemini-4-hydrogen); not supported by Orchestrator.
modelstring–Optional model override. Known: Gemini 4 Hydrogen (Low), Gemini 4 Hydrogen (Medium), Gemini 4 Hydrogen (High), Gemini 4 Hydrogen (XHigh), Gemini 4 Argon (Low), Gemini 4 Argon (Medium), Gemini 4 Argon…
promptstring–Custom review instructions or focus areas (optional)
timeoutinteger–Maximum execution time in milliseconds
titlestring–Optional title for the review summary
uncommittedboolean–Review staged + unstaged + untracked changes (working tree)
workingDirstring–Working directory to run the review in

No output schema declared.

No examples provided.

version ~13

Display version and system information

Input schema present but exposes no named parameters.

NameTypeReqDescription
agyClistring––
mcpServerstringyes–
nodeJsstringyes–
platformstringyes–

No examples provided.

Install

How do I install the Antigravity MCP Server server?

Antigravity MCP Server runs locally as an npm package, launched with npx -y @trishchuk/antigravity-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @trishchuk/antigravity-mcp-server

# add to Claude Code
claude mcp add x51xxx-antigravity-mcp-server -- npx -y @trishchuk/antigravity-mcp-server
Common questions

What is the Antigravity MCP Server server?

Antigravity MCP Server is listed in the public MCP registry as io.github.x51xxx/antigravity-mcp-server. Hand work from Claude Code or Cursor to Google Antigravity CLI: delegation, reviews, digests. This page covers its npm package (@trishchuk/antigravity-mcp-server).

Is the Antigravity MCP Server server safe to use?

Antigravity MCP Server scores 66 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Antigravity MCP Server server expose?

Antigravity MCP Server exposes 15 tools: ask-antigravity, batch-antigravity, review-changes, plan-antigravity, brainstorm, and 10 more. Their descriptions and schemas cost roughly 3,878 tokens of context every time the server is loaded.

Is the Antigravity MCP Server server still maintained?

Antigravity MCP Server is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Antigravity MCP Server server under?

Antigravity MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Antigravity MCP Server server?

VerifyMCP ran 16 checks on Antigravity MCP Server, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.