About Gemini CLI MCP Servers
Gemini CLI MCP Servers is an MCP server published by ksprashu in the AI category: a bunch of MCP Servers I've created for use with Gemini CLI.
The repository has 10 stars and 6 forks, with the last commit 11 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
Install
git clone https://github.com/ksprashu/gemini-cli-mcp-serversThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Gemini CLI MCP Servers
Powered by Claude · Grounded in docs
Security checks
Static checks derived from the repository 5 days ago. Heuristics on the source, not an audit.
- ✓README presentThe repository ships documentation.
- ✓License declaredUsable under a stated license.
- !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
- ✓Dependencies pinnedA lockfile pins dependency versions.
- ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
README
Gemini CLI MCP Servers
This repository contains a collection of custom MCP (Multi-Capability Provider) servers designed to extend the functionality of the Gemini CLI.
Initial Project Setup
Before installing the individual servers, it's recommended to set up the project environment.
-
Clone the Repository (if you haven't already):
# Replace with the actual repository URL git clone https://github.com/your-username/gemini-cli-mcp-servers.git cd gemini-cli-mcp-servers -
Set up the Virtual Environment: This project uses
uvfor environment and package management.# Create and activate a virtual environment uv venv source .venv/bin/activate # Install base dependencies uv pip install -e .
Available Servers
Below is a list of the available servers and how to install them into the Gemini CLI. The recommended installation method is using the fastmcp command-line tool.
1. PromptGen (/promptgen)
An MCP server to help refine user prompts based on a set of prompt engineering best practices.
- To Install:
fastmcp install gemini-cli promptgen_server/main.py --name promptgen - Usage:
> /promptgen 'your simple prompt idea'
2. SuperAgent (/superagent)
A powerful orchestrator agent that follows an "Analyze -> Decide -> Formulate -> Delegate" loop to accomplish complex tasks by dispatching specialist agents.
- To Install:
fastmcp install gemini-cli superagent_server/main.py --name superagent - Usage:
> /superagent 'your high-level goal here'
Important Setup for SuperAgent:
The SuperAgent requires a dedicated temporary directory for its operations. Please create the following directory in your home directory:
mkdir -p ~/tmp/gemini-tasks/
Additionally, you must inform the Gemini CLI about this new directory so it can write scratch files outside the current working directory. You can do this in one of two ways:
- Using the Gemini CLI command:
/directory add ~/tmp/gemini-tasks/ - Manually editing
settings.json: Add the following entry to yoursettings.jsonfile, located in your.gemini/folder:
(Note: Replace"context": { "ignore": [], "includeDirectories": [ "/Users/ksprashanth/tmp/gemini-tasks" ] },/Users/ksprashanth/tmp/gemini-taskswith the actual absolute path to yourgemini-tasksdirectory if it's different.)
Disclaimer
This is not an officially supported Google product.
License
This project is licensed under the Apache License, Version 2.0. See the LICENSE file for details.
README fetched from the repository 5 days ago. The original is authoritative.