Antigravity MCP Bridge
Related Servers
Alternatives to Antigravity MCP Bridge
No user-submitted related servers found.
Related Servers
- AlicenseBqualityBmaintenanceEnables a local Codex chat to ask a second opinion, review staged, unstaged, or revision-based diffs, and delegate coding tasks to the Antigravity CLI running in isolated or disposable workspaces. Supports starting, polling, retrieving, and cancelling tasks with returned answers, diffs, changed-file lists, exit codes, and time/output limits, while never auto-applying returned patches.81MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI clients to run Google Antigravity coding sub-agents as MCP tools, with synchronous and asynchronous execution, task polling, and sandboxed Docker workspace isolation.-
- AlicenseAqualityCmaintenanceEnables 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.3MIT
- AlicenseBqualityAmaintenanceAn MCP bridge that lets Codex delegate long-running agent work to the Antigravity CLI, providing observable and resumable tool-based execution with project scoping.1481 PyPI12MIT
- AlicenseNot gradedqualityAmaintenanceEnables Codex or Claude Code to orchestrate persistent Antigravity CLI workers as independent implementers and testers within restricted workspace roots. It supports asynchronous task dispatch, progress polling, result inspection, follow-up messages, and cancellation with bounded, audited local event logging.150 npm1MIT
- AlicenseNot gradedqualityFmaintenanceEnables MCP-compatible clients like Codex to delegate tasks to the Antigravity CLI, using ConPTY on Windows to reliably capture responses.3MIT
TDQS
Scored across 23 tools
Tools generally target distinct lifecycle stages (run/resume/cancel, preview/read_patch/read_result, test/verify/integrate), but several reading/status tools have adjacent purposes. The descriptions help separate result vs read_result and preview vs read_patch, though an agent could still confuse them.
All tools consistently use the antigravity_ prefix with snake_case, which makes the set predictable. Most names are verb_noun or verb_noun-phrase, but some are noun-only query tools (usage, status, tasks, events, result, sessions), a minor deviation from a strict pattern.
23 tools is heavy for a single MCP server and sits in the borderline 16-25 range. The domain is complex, but several output-reading and status tools could be consolidated, making the surface feel somewhat over-scoped.
The surface covers model selection, task lifecycle, file listing, patch/result reading, testing, verification, integration, and cleanup. Minor gaps exist, such as no explicit authentication/login tool or direct source-file read outside task artifacts, but core workflows are covered.