Skip to main content
Glama
Sign In
Antigravity MCP Server

Antigravity MCP Server

by x51xxx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

ask-antigravity

Destructive

Delegate multi-step coding tasks to Google Antigravity CLI, selecting models, agent modes, workspaces, and sessions, or resume conversations and generate read-only plans and code reviews.

Instructions

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

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "ask-antigravity"
  }
}

Input Schema

NameRequiredDescriptionDefault
cdNoWorking directory
modeNoAgent mode (--mode): accept-edits, auto (sandboxed autonomy; not available on every account), or plan (answers go into a plan artifact).
modelNoOptional 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), Gemini 4 Argon (Medium), Gemini 4 Argon (High), Gemini 4 Carbon (Low), Gemini 4 Carbon (Medium), Gemini 4 Carbon (High), Orchestrator (Argon), Orchestrator (Carbon), Gemini 3.8 Flash (Low), Gemini 3.8 Flash (Medium), Gemini 3.8 Flash (High), Claude Opus 5.5 (Low), Claude Opus 5.5 (Medium), Claude Opus 5.5 (High), Claude Sonnet 5.5 (Low), Claude Sonnet 5.5 (Medium), Claude Sonnet 5.5 (High), GPT-OSS 120B (Medium). If omitted, uses your Antigravity CLI default.
dryRunNoReturn the resolved CLI argv as JSON without spawning agy.
effortNoReasoning 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.
promptYesTask or question. Reference files by path — agy reads them with its own tools.
addDirsNoAdditional workspace directories (--add-dir, repeatable).
sandboxNo--sandbox: run with terminal restrictions enabled.
timeoutNoMaximum execution time in milliseconds (default 600000)
sessionIdNoInternal session ID for conversation continuity (workspace-isolated).
workingDirNoWorking directory for execution (alias of cd)
resetSessionNoClear session context before execution. Starts fresh conversation.
responseModeNoResponse verbosity: "clean" returns only the final answer (default), "full" includes the stderr execution log.clean
continueLatestNoUse --continue to resume the most recent conversation.
conversationIdNoNative Antigravity conversation ID to resume (--conversation). Overrides sessionId lookup.
skipPermissionsNo⚠️ --dangerously-skip-permissions: auto-approve all tool permission requests.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, openWorldHint=true, and readOnlyHint=false, so the safety posture is established without the description. The description adds only 'print mode', which usefully signals a non-interactive subprocess returning a final answer, but says nothing about permission approval flow, default timeout behavior, or what side effects the spawned agent can have on the workspace — all of which live only in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the action and target, with no filler or repetition. It is efficient, though the trailing capability list is largely a restatement of parameter names and could have carried a differentiator instead.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 16-parameter tool the description is thin, but the schema is fully documented and annotations cover safety, so the agent has what it needs to call the tool. The one gap is that no output schema exists and the description does not characterize the return shape beyond 'print mode', leaving responseMode's effect to be discovered from the parameter description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description's phrase 'model selection, conversation resume, and workspace controls' merely groups parameter families that the schema already documents in detail (model IDs, effort levels, conversationId vs sessionId precedence, dryRun, skipPermissions); it adds no format or precedence meaning of its own.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (Execute) and resource (Google Antigravity CLI / agy), plus the operating mode (print mode) and the capability families it covers (model selection, conversation resume, workspace controls). An agent can tell this is the synchronous single-prompt runner, but the description never names the sibling it differs from, even though batch-antigravity, bg-antigravity, and delegate-antigravity all sound adjacent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'print mode' suggests a one-shot, non-interactive invocation, which is the main hint for choosing this over a background or batch variant. There is no explicit when-to-use, no when-not, and no pointer to an alternative for long-running or multi-prompt work.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools