Skip to main content
Glama

Run Antigravity prompts in parallel

antigravity_swarm

Run multiple Antigravity prompts concurrently in isolated workers. Each worker executes independently; failures don't affect others. Combine results for parallel sub-tasks.

Instructions

Run several Antigravity (Gemini 3.5 Flash High) prompts IN PARALLEL.

Fans the prompts out to independent agy workers that run truly concurrently (each in its own isolated state dir, so they never race), capped at max_concurrency. Returns one combined text block with every worker's answer, labelled by index. A worker that fails is reported in place — the others still return (error isolation).

Use this to parallelise independent, cheap sub-tasks (e.g. summarise N files, ask the same question about N repos). For a single prompt use antigravity_ask.

SECURITY: this launches N unsandboxed agy agents at once — N times the prompt-injection surface of a single call (see the module SECURITY note). Only use it with trusted prompts on trusted content.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptsYesOne prompt per parallel worker.
workspacesNoWorking directory per worker. Omit for the server cwd; pass a 1-item list to point every worker at the same dir; pass one entry per prompt to give each worker its own dir.
max_concurrencyNoMax workers running at once (default 4). Higher = faster but more quota/rate-limit pressure and more agents at once.
timeout_sNoPer-worker timeout in seconds. Default 180.
watchNoIf true, open the live "Antigravity Swarm" dashboard window (one row per worker; click a row to open that agent's full step log beside it).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Discloses parallel execution, error isolation, combined text output, security risks (N times prompt-injection surface), and dashboard option, far beyond what annotations provide.

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

Conciseness5/5

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

Concise (~150 words), well-structured with paragraphs and bullet points, front-loaded with core purpose, every sentence earns its place.

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

Completeness5/5

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

Given 5 parameters, required prompts, output schema exists, and complexity of parallel execution, the description completely covers choice and usage without gaps.

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

Parameters5/5

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

Adds meaningful context to all parameters: prompts are independent, workspaces options explained, max_concurrency ties to quota pressure, and watch opens dashboard. Schema coverage is 100% but description adds value.

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

Purpose5/5

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

The description starts with a clear verb ('Run'), resource ('Antigravity prompts'), and mode ('IN PARALLEL'), and explicitly distinguishes from sibling tool antigravity_ask for single prompts.

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

Usage Guidelines5/5

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

Explicitly states when to use ('parallelise independent, cheap sub-tasks') and when not to ('For a single prompt use antigravity_ask'), along with security caveats.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SinanTufekci/antigravity-intern'

If you have feedback or need assistance with the MCP directory API, please join our Discord server