Gemini Bridge

Gemini Bridge

Lightweight MCP server enabling Claude to interact with Gemini CLI.

66
Stars
6
Forks
5
Releases

Overview

Gemini Bridge is a lightweight MCP (Model Context Protocol) server that acts as a bridge between Claude Code (and other MCP-compatible clients) and Google's Gemini AI via the official Gemini CLI. It operates statelessly, with no sessions or caching, and supports simple, robust workflows for code analysis and file review. The server exposes two core tools: consult_gemini, for basic prompts and queries, and consult_gemini_with_files, for analyzing multiple files with optional attachments. It provides zero API costs by delegating all Gemini interactions to the CLI, and it implements a production-ready timeout mechanism (default 60 seconds) configurable via GEMINI_BRIDGE_TIMEOUT. Inline-mode file transfers are capped at ~256 KB per file and ~512 KB per request; oversized files are truncated with a warning, and larger payloads can be handled by mode="at_command". It requires minimal dependencies (mcp>=1.0.0 and Gemini CLI) and supports various deployment methods (uvx-based, traditional pip installation). It is designed for universal MCP compatibility across clients like Claude Code, Cursor, VS Code, Windsurf, Cline, Void, Cherry Studio, Augment, Roo Code, Zencoder, and more.

Details

Owner
eLyiN
Language
Python
License
MIT License
Updated
2025-12-07

Features

Direct Gemini CLI Integration

Zero API costs using the official Gemini CLI for all interactions.

Simple MCP Tools

Two core functions for basic queries and file analysis.

Stateless Operation

No sessions, caching, or complex state management.

Production Ready Timeout

Robust error handling with configurable 60-second timeouts.

Minimal Dependencies

Only requires mcp>=1.0.0 and Gemini CLI.

Easy Deployment

Support for both uvx and traditional pip installation.

Universal MCP Compatibility

Works with any MCP-compatible AI coding assistant.

Attachment Guardrails

Inline transfers capped at ~256 KB per file and ~512 KB per request; mode 'at_command' handles larger payloads.

Audience

AI coding assistantsEnable Gemini CLI access within MCP workflows for code-related tasks.
MCP client developersProvide a reliable bridge for Gemini CLI integration with MCP-compatible clients.
IDE usersUse a lightweight bridge to access Gemini via MCP inside editors.

Tags

MCPGeminiCLIClaudeCode analysisfile analysisstatelesstimeoutuvxdeploymentintegration