Google PageRank for AI agents. 25,000+ tools indexed.

gemini-cli-mcp by xjoker

#577 of 1753 by xjoker
38 score

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command injection.

Ranked #577 out of 1753 indexed tools.Actively maintained with commits in the last week.
🔑
Is this your tool? Claim this listing to add maintainer context, get a verified badge, and unlock analytics.
Claim listing →

Signal Breakdown

Installs 2
Freshness 1d ago
Issue Health 50%
Stars 4
Platform Breadth 1 platform
Contributors 1
Description Detailed

How to Improve

Contributors medium impact

Single-contributor projects carry bus-factor risk — welcoming contributors boosts confidence

Stars low impact

Low star count — promote the project, write docs, and engage the community to drive adoption

Platforms medium impact

Only 1 platform listed — publishing to more platforms improves your score

Badge

AgentRank score for gemini-cli-mcp by xjoker
[![AgentRank](https://agentrank-ai.com/api/badge/skill/glama-xjoker--gemini-cli-mcp)](https://agentrank-ai.com/skill/glama-xjoker--gemini-cli-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/skill/glama-xjoker--gemini-cli-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/badge/skill/glama-xjoker--gemini-cli-mcp" alt="AgentRank"></a>

Supported Platforms

MCP

From the README

# gemini-cli-mcp

[中文文档](./README.zh-CN.md)

A secure [MCP](https://modelcontextprotocol.io/) server that wraps Google's [Gemini CLI](https://github.com/google-gemini/gemini-cli). It lets Claude Code (or any MCP client) call Gemini models using your local OAuth session — no API key required.

## Highlights

- **Secure** — `spawn(shell:false)` on Unix; controlled `shell:true` + arg escaping on Windows. No command injection.
- **Cross-platform** — macOS, Linux, Windows. Auto-resolves `.cmd` wrappers and forces UTF-8.
- **Activity-based timeout** — idle timer resets on each output chunk. Long thinking won't be killed; stuck 429 retries will.
- **Low token overhead** — replaces Gemini's ~8 800-token default system prompt with a minimal one (~50 tokens).
- **Clean output** — internally uses `stream-json` and parses structured responses. No stdout noise pollution.
- **2 tools only** — `gemini_query` + `gemini_info`. Minimal context-window footprint for the host AI.

## Prerequisites

1. **No
Read full README on GitHub →