Antigravity Delegate
Related Servers
Alternatives to Antigravity Delegate
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceMCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.6143 npm68MIT
- AlicenseBqualityBmaintenanceEnables MCP clients such as Claude Code and Cursor to delegate long multi-step coding tasks to Google Antigravity CLI, generate read-only plans and code reviews, digest large codebases, and manage background sessions in isolated git worktrees.15287 npm2MIT
- AlicenseAqualityCmaintenanceLets MCP clients such as Claude Code, Claude Desktop, Cursor, or Codex hand tasks to the Antigravity CLI (agy) so the work runs on the user's Antigravity plan instead of the client's. Exposes tools for delegated coding tasks and reviews, web search with sources, image/PDF analysis, shell command generation or execution, brainstorming, and model/quota checks.7MIT
- AlicenseAqualityDmaintenanceLets Claude Code use Google's Antigravity CLI (agy) to review plans or execute them in isolated git worktrees, with safety controls like secret scanning.4MIT
- AlicenseNot gradedqualityBmaintenanceLets Claude Code or any MCP client hand work to the Google Antigravity CLI in locked plan, read-only ask, or full edit modes, with background jobs that survive disconnects, quota and model checks, and a wake hook that notifies the client when a job finishes. It runs as a dependency-free Node.js file on macOS, Windows and Linux, enforcing plan mode through agy's own read-only flag and reporting any files changed during ask or edit runs.3MIT
- AlicenseAqualityBmaintenanceExposes Google's Antigravity CLI agent as MCP tools, letting any MCP host run persistent, resumable conversations with streamed progress and per-call workspace, model, effort, and mode overrides. Enables agents to delegate coding and shell-capable tasks to the Antigravity agent from OpenCode, Claude Desktop, Cursor, or custom agents.7MIT
TDQS
Scored across 3 tools
Each tool maps to a clearly distinct action in the delegation lifecycle: start/resume a delegation (delegate), abort one (cancel), and diagnose setup failures (doctor). The descriptions explicitly scope when to use each, including the 'never shell out to agy' guardrail, so an agent can select without ambiguity.
All names are single lowercase words with no mixed casing or prefixes, so the set is predictable. The only deviation is that 'doctor' is a noun while 'delegate' and 'cancel' are verbs, a minor break in the verb pattern.
Three tools is minimal but well-matched to a narrow proxy purpose: one action tool, one lifecycle-control tool, one diagnostic. Nothing extraneous is present, though the surface is thin enough that a fourth helper (e.g. list sessions) could be justified.
The core lifecycle is covered: start/resume delegation, cancel an in-flight run, and troubleshoot setup. The main gap is discoverability — there is no way to list or query active/recent session IDs, so an agent must track sessionIds itself, and resume is only reachable by re-invoking delegate.