MCPgee
MCPgee
MCPgeeMCPgee

Gemini CLI MCP

v1.0.0•Developer Tools•stable

A bunch of MCP Servers I've created for use with Gemini CLI

gemini-cli-mcp-serversmcpai-integration
Share:
11
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Gemini CLI MCP?

Gemini CLI MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to bunch of mcp servers i've created for use with gemini cli

A bunch of MCP Servers I've created for use with Gemini CLI

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A bunch of MCP Servers I've created for use with Gemini CLI

Use Cases

Use custom MCP servers with Google Gemini CLI.
Extend Gemini capabilities with AI tools.
ksprashu

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedJan 24, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx gemini-cli-mcp-servers

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Gemini CLI MCP

Gemini CLI MCP Servers is a collection of custom MCP servers designed for use with Google's Gemini CLI, including a PromptGen server that refines prompts using best practices and a SuperAgent orchestration server that breaks complex goals into specialist sub-tasks using an Analyze-Decide-Formulate-Delegate workflow.

Prerequisites

  • Python 3.10+ installed
  • uv virtual environment manager installed (https://github.com/astral-sh/uv)
  • fastmcp CLI tool installed: pip install fastmcp
  • Gemini CLI installed and authenticated: npm install -g @google/gemini-cli
  • Git to clone the repository
1

Clone the Repository

Clone the Gemini CLI MCP Servers repository and enter the project directory.

git clone https://github.com/ksprashu/gemini-cli-mcp-servers.git
cd gemini-cli-mcp-servers
2

Create and Activate a Virtual Environment

Create a uv-managed virtual environment and activate it. This isolates the server dependencies from your system Python.

uv venv
source .venv/bin/activate  # macOS/Linux
# .venv\Scripts\activate   # Windows
3

Install the Package

Install the MCP servers package in editable mode using uv pip.

uv pip install -e .
4

Install Servers into Gemini CLI

Use the fastmcp install command to register each server with Gemini CLI. After installation, the servers appear as slash commands inside the Gemini CLI session.

# Install the PromptGen server
fastmcp install gemini-cli promptgen_server/main.py --name promptgen

# Install the SuperAgent orchestration server
fastmcp install gemini-cli superagent_server/main.py --name superagent
5

Create the SuperAgent Working Directory

The SuperAgent server uses ~/tmp/gemini-tasks/ as a working directory for task breakdown and delegation artifacts. Create it before running the server.

mkdir -p ~/tmp/gemini-tasks/
6

Add the Working Directory to Gemini CLI Context

Add the tasks directory to Gemini CLI's context so the SuperAgent can read and write task files. Either use the /directory command inside a Gemini session or edit the settings file directly.

# Inside a Gemini CLI session:
/directory add ~/tmp/gemini-tasks/

# Or edit ~/.gemini/settings.json:
# Add ~/tmp/gemini-tasks/ to context.includeDirectories

Gemini CLI MCP Examples

Client configuration

Gemini CLI settings.json with the tasks directory added to context and both MCP servers registered.

{
  "context": {
    "includeDirectories": [
      "~/tmp/gemini-tasks/"
    ]
  },
  "mcpServers": {
    "promptgen": {
      "command": "python",
      "args": ["promptgen_server/main.py"],
      "cwd": "/path/to/gemini-cli-mcp-servers"
    },
    "superagent": {
      "command": "python",
      "args": ["superagent_server/main.py"],
      "cwd": "/path/to/gemini-cli-mcp-servers"
    }
  }
}

Prompts to try

Commands to use inside a Gemini CLI session once the MCP servers are installed.

- "/promptgen 'Write a Python function that parses JSON'" — refines the prompt using best practices
- "/superagent 'Build a REST API for a todo app with authentication'" — orchestrates multi-step task delegation
- "/promptgen 'Explain machine learning to a beginner'" — improves clarity and specificity of the prompt
- "/superagent 'Analyse this codebase and identify performance bottlenecks'" — runs the Analyze-Decide-Formulate-Delegate workflow
- "/promptgen 'Create a database schema for an e-commerce platform'" — applies prompt engineering techniques

Troubleshooting Gemini CLI MCP

'fastmcp: command not found' when trying to install servers

Install fastmcp into your virtual environment with 'pip install fastmcp' or 'uv pip install fastmcp', then ensure the .venv/bin directory is on your PATH or activate the virtual environment before running fastmcp.

Servers appear installed but slash commands are not available in Gemini CLI

Restart the Gemini CLI session after installing servers — fastmcp installs are picked up on session start, not hot-reloaded. Run 'gemini' again and check if /promptgen and /superagent appear in the command list.

SuperAgent fails to write task files or reports a missing directory

Create the required working directory with 'mkdir -p ~/tmp/gemini-tasks/' and add it to Gemini CLI context with '/directory add ~/tmp/gemini-tasks/' inside a Gemini session before invoking /superagent.

Frequently Asked Questions about Gemini CLI MCP

What is Gemini CLI MCP?

Gemini CLI MCP is a Model Context Protocol (MCP) server that bunch of mcp servers i've created for use with gemini cli It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Gemini CLI MCP?

Follow the installation instructions on the Gemini CLI MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Gemini CLI MCP?

Gemini CLI MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Gemini CLI MCP free to use?

Yes, Gemini CLI MCP is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Gemini CLI MCP Alternatives — Similar Developer Tools Servers

Looking for alternatives to Gemini CLI MCP? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

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 in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "gemini-cli-mcp-servers": { "command": "npx", "args": ["-y", "gemini-cli-mcp-servers"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Gemini CLI MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides