# Gemini CLI

> Use this tool when you need to analyze large files and codebases, or safely test code execution, and want to leverage Google's Gemini CLI for advanced reasoning capabilities. It solves problems such as large-scale code analysis and safe script testing by providing a programmable interface for Gemini queries, sandbox-mode code execution, and structured response handling. The tool accepts file references and commands as input and outputs formatted results, making it ideal for building AI assistants that require automated access to Gemini's features.

Canonical page: https://skillsregistry.net/skills/jamubc-gemini-cli  
JSON: https://api.skillsregistry.net/v1/skills/jamubc-gemini-cli

## Description

This MCP server provides integration with Google's Gemini CLI, enabling AI assistants to leverage Gemini's massive token window for analyzing large files and codebases using the @ syntax for file references. Built using TypeScript with the Model Context Protocol SDK, it offers tools for general Gemini queries, sandbox-mode code execution for safe testing, and structured response handling with behavioral flags that control AI interaction patterns including context suppression and output formatting. The implementation features proper argument handling for the Gemini CLI, progress monitoring for long-running operations, slash command support for direct user interaction, and specialized sandbox capabilities for executing potentially risky code in an isolated environment, making it valuable for large-scale code analysis, safe script testing, and building AI assistants that need access to Gemini's advanced reasoning capabilities without manual CLI usage.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-04-30

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/jamubc-gemini-cli)
- **Repository:** <https://github.com/jamubc/gemini-mcp-tool>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "jamubc-gemini-cli"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jamubc-gemini-cli` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jamubc-gemini-cli/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt