Enterprise DNA
M MCP Servers Developer low

sshahzaiib/agy-bridge

by Various

MCP 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

S

MCP

sshahzaiib/agy-bridge

Added 19 June 2026

#agy #ai-agents #antigravity-cli #claude #claude-code #delegation #gemini #mcp

Overview

Agy-bridge is an MCP bridge that allows Claude Code to offload heavy tasks to the Antigravity CLI (agy). It handles model routing with fallback, maintains session continuity, and truncates outputs to conserve Claude's context window and token usage.

Best for

Best for
Developers using Claude Code who need to offload heavy or specialized tasks to external CLI tools

Use cases

  • Delegating resource-intensive operations from Claude Code to specialized CLI tools
  • Routing tasks to fallback models when the primary model is unavailable or overloaded
  • Preserving conversation context across long-running or multi-step agent sessions

How to use

Install

claude mcp add-json -s user agy-bridge '{"command":"npx","args":["-y","agy-bridge"],"timeout":600000}' && curl -o CLAUDE.md https://raw.githubusercontent.com/sshahzaiib/agy-bridge/main/CLAUDE.md

Tools exposed

  • analyze_files
  • deep_search
  • web_lookup
  • adversarial_review
  • follow_up
  • delegate

Tested with

Claude Code

Example client config

{\n  "command": "npx",\n  "args": [\n    "-y",\n    "agy-bridge"\n  ],\n  "timeout": 600000\n}

Notes

Agy-bridge is an MCP bridge that allows Claude Code to offload heavy tasks to the Antigravity CLI (agy). It handles model routing with fallback, maintains session continuity, and truncates outputs to conserve Claude’s context window and token usage.

14 stars on GitHub. Last updated 2026-06-19. Licensed MIT.

Use cases

  • Delegating resource-intensive operations from Claude Code to specialized CLI tools
  • Routing tasks to fallback models when the primary model is unavailable or overloaded
  • Preserving conversation context across long-running or multi-step agent sessions

Pros

  • Reduces token consumption by truncating verbose CLI outputs
  • Provides fallback routing for more reliable task execution
  • Maintains session state across delegated operations

Cons

  • Limited to 14 GitHub stars, indicating a small user base and potential instability
  • Depends on both Claude Code and Antigravity CLI, adding setup complexity
  • Output truncation may lose important details in some use cases

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Reduces token consumption by truncating verbose CLI outputs
  • Provides fallback routing for more reliable task execution
  • Maintains session state across delegated operations

Cons

  • Limited to 14 GitHub stars, indicating a small user base and potential instability
  • Depends on both Claude Code and Antigravity CLI, adding setup complexity
  • Output truncation may lose important details in some use cases

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks