Gemini Terminal Agent

@Nghiauet

About Gemini Terminal Agent

create agent with mcp server

#mcp-agent #gemini-terminal-agent #terminal-agent

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-agent-nghiauet": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Gemini Terminal Agent?

Gemini Terminal Agent is a terminal-based agent that uses Google’s Gemini model and integrates real‑time web search via Google Custom Search Engine. It is intended for developers and power users who want a conversational AI interface directly in their terminal.

How to use Gemini Terminal Agent?

Install Python 3.9+, clone the repository, create a virtual environment, install dependencies, and add your API keys to a .env file. Run python main.py to start the agent. Type prompts or questions, and use commands such as help, clear, and exit.

Key features of Gemini Terminal Agent

Conversational AI interface using Google’s Gemini models
Web search integration for up‑to‑date information
Conversation history maintained across turns
Advanced search options (domain filtering, exclusions, time range)
Clean, modular architecture that is easy to extend

Use cases of Gemini Terminal Agent

Ask questions and receive Gemini‑powered answers from the terminal
Perform real‑time web searches without leaving the command line
Maintain multi‑turn context for deeper technical discussions

FAQ from Gemini Terminal Agent

What is the difference between Gemini Terminal Agent and the Gemini web UI?

Gemini Terminal Agent runs locally in your terminal and adds built‑in web search capabilities, which the standard Gemini web interface does not provide.

What are the runtime dependencies?

Python 3.9 or higher, a Google Gemini API key, and a Google Custom Search Engine (CSE) API key with its corresponding CSE ID.

Where is conversation history stored?

History is kept in memory for the duration of the session. It can be cleared by typing the clear command.

What search features are available?

The agent supports both basic and advanced web search, including domain filtering, site exclusion, and time‑range options.

How do I configure the model and search settings?

All settings are managed through the .env file, where you can set the model name, maximum concurrent requests, timeouts, and cache TTL.

Frequently asked questions

What is the difference between Gemini Terminal Agent and the Gemini web UI?

Gemini Terminal Agent runs locally in your terminal and adds built‑in web search capabilities, which the standard Gemini web interface does not provide.

What are the runtime dependencies?

Python 3.9 or higher, a Google Gemini API key, and a Google Custom Search Engine (CSE) API key with its corresponding CSE ID.

Where is conversation history stored?

History is kept in memory for the duration of the session. It can be cleared by typing the `clear` command.

What search features are available?

The agent supports both basic and advanced web search, including domain filtering, site exclusion, and time‑range options.

How do I configure the model and search settings?

All settings are managed through the `.env` file, where you can set the model name, maximum concurrent requests, timeouts, and cache TTL.

Comments

Basic information

More AI & Agents MCP servers

mcp-hfspace MCP Server 🤗

evalstate

MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.

387

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

Shell and Coding agent for Claude and other mcp clients

rusiaaman

Shell and coding agent on mcp clients

666

bsv.cx

Andy Rowe

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K