Related Servers

No user-submitted related servers found.

Related Servers

• agy-ui-mcp

  qdzsh

  A

  license

  A

  quality

  C

  maintenance

  Delegates frontend/UI refinement to Gemini via agy CLI, using iterative vision loops and diff-gating to realign UIs to design mockups without affecting backend code.

  Updated 4 months ago (2026-06-19 06:24 UTC)

  3

  MIT

• Antigravity Worker MCP

  getio0909

  A

  license

  -Not graded

  quality

  B

  maintenance

  Enables STDIO-compatible AI assistants to queue coding work onto the official Google Antigravity CLI and track status, read reports or patches, query capabilities, or cancel running tasks without blocking. Supports trusted direct execution plus optional isolated or read-only modes depending on the platform.

  Updated 10 days ago (2026-10-02 21:37 UTC)

  MIT

• Antigravity Codex MCP

  ustc-fyk

  A

  license

  A

  quality

  B

  maintenance

  A controlled Model Context Protocol bridge that lets OpenAI Codex delegate work to Google Antigravity CLI on demand, with project-scoped opt-in and read-only delegation.

  Updated 2 months ago (2026-08-20 02:16 UTC)

  15

  1

  MIT

• Codex Antigravity Subagent MCP

  zamatewi-cell

  A

  license

  A

  quality

  A

  maintenance

  Lets Codex delegate tasks to the Google Antigravity CLI (agy) with background job execution, live progress tracking, a visual dashboard, and structured error diagnostics.

  Updated a month ago (2026-09-09 03:02 UTC)

  8

  MIT

• sub-antigravity

  ZorIgn

  A

  license

  A

  quality

  C

  maintenance

  Enables AI harnesses to delegate code analysis, modification, testing, and long-running tasks to the locally installed Antigravity CLI via stdio MCP, with job status tracking and conversation continuity.

  Updated a month ago (2026-09-05 03:51 UTC)

  3

  MIT

• antigravity-cli

  LoliLin

  A

  license

  -Not graded

  quality

  C

  maintenance

  Enables a chat agent to drive the official Antigravity CLI headlessly: start and later resume tasks in separate agent contexts, audit what each run actually executed, and complete Google sign-in on a machine with no browser. It also surfaces permission mode and denial hints so a run that silently did nothing is never mistaken for success.

  Updated 13 days ago (2026-09-30 12:52 UTC)

  MIT