A
licenseB
qualityB
maintenanceAn MCP bridge that lets Codex delegate long-running agent work to the Antigravity CLI, providing observable and resumable tool-based execution with project scoping.
14
39 PyPI
17
MIT
Antigravity Codex MCP
by ustc-fyk
Related Servers
Alternatives to Antigravity Codex MCP
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenanceEnables OpenAI Codex to delegate tasks to Google Antigravity CLI, running them headlessly and polling for results.4MIT
- AlicenseNot gradedqualityBmaintenanceEnables Codex users to delegate engineering, refactoring, auditing, and test execution tasks to Google Antigravity CLI as a persistent autonomous subagent, with tools for managing sessions and running prompts.1MIT
- AlicenseNot gradedqualityCmaintenanceA local-STDIO MCP server that lets Codex invoke the Antigravity CLI from any project, with project-owned routing guidance and enforceable policies.MIT
- AlicenseNot gradedqualityCmaintenanceEnables Codex to delegate coding and code-review tasks to Gemini through a configurable relay using the Antigravity SDK. Supports model discovery, read-only or edit modes, and live task progress in a side panel.MIT
- MIT
TDQS
A4/5.0
Scored across 15 tools
Disambiguation5/5
Each tool has a clearly distinct purpose: project lifecycle (enable, disable, status), session management (start, get active, sync, transcript), conversation actions (ask, continue, review), and execution (execute, get run). No two tools appear to perform the same function; even the conversation-related tools are differentiated by mode (read-only analysis, continuation, review).
Naming Consistency5/5
All tools follow a consistent verb_noun pattern with the 'antigravity_' prefix (e.g., list_sessions, enable_project, get_transcript). The naming is uniform and predictable, making it easy for an agent to infer tool purpose from the name alone.
Tool Count5/5
15 tools is well-scoped for a server that manages AGY sessions, project configuration, transcripts, and executions. Each tool covers a distinct operational need without redundancy, and the count is within the ideal range for a feature-complete MCP server.
Completeness5/5
The tool surface covers the full lifecycle: project enable/disable/status, session creation and retrieval, transcript syncing and retrieval, conversation actions (ask, continue, review), and execution management (execute and get_run). No obvious gaps exist—both administrative and interactive workflows are supported.
Maintenance
ActivityInactive
ResponsivenessNo recent community issues