ToolsForMCPServer-extension
Simplified Google Workspace Automation with Gemini CLI Extensions
claude mcp add --transport stdio tanaikech-toolsformcpserver-extension npx -y tanaikech-toolsformcpserver-extension \ --env GEMINI_API_KEY="Your Gemini API key" \ --env MCP_WEB_APPS_URL="https://script.google.com/macros/s/your-script-id/exec?accessKey=your-access-key"
How to use
This MCP server extension enables Gemini CLI users to access the ToolsForMCPServer capabilities via a Gemini extension-based MCP server. After deploying the Google Apps Script web app and configuring the required environment variables, you can invoke the MCP tools from Gemini using the /mcp command. The server exposes a suite of tools originally provided by ToolsForMCPServer, such as data automation helpers, Google Sheets and Docs-related operations, and other generic MCP utilities that can be commanded through natural-language prompts. Once running, Gemini will route prompts to the ToolsForMCPServer backend hosted by the Apps Script Web App URL and return structured results.
To use the tools, ensure your GEMINI_API_KEY is set for authenticating with Gemini services and MCP_WEB_APPS_URL points to your deployed Web App endpoint. In the Gemini CLI session, run /mcp to load the available tools, then issue prompts to perform tasks such as data extraction, transformation, or Google Workspace automation using natural language commands.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- Gemini CLI installed and configured
- Access to the internet to install dependencies
Step-by-step instructions:
- Install the Gemini CLI if you haven’t already:
npm install -g @google/gemini-cli
- Install this MCP server extension via Gemini:
gemini extensions install https://github.com/tanaikech/ToolsForMCPServer-extension
- Deploy and configure the underlying ToolsForMCPServer backend (Google Apps Script Web App):
- Create and deploy the Apps Script Web App as described in the repository’s deployment steps.
- Copy the Web App URL (endpoints) and set it as MCP_WEB_APPS_URL.
- Ensure you have a Gemini API key; export it or set it in your environment.
- Set required environment variables:
export GEMINI_API_KEY="{Your API key}"
export MCP_WEB_APPS_URL="https://script.google.com/macros/s/###/exec?accessKey=sample"
- Run the MCP server via the extension (the extension is installed globally by the Gemini CLI):
gemini
Then within Gemini, load the MCP server (using /mcp) and start issuing prompts to interact with ToolsForMCPServer.
Additional notes
Notes and tips:
- The MCP server is backed by a Google Apps Script Web App; ensure the app is deployed with the correct permissions (Execute as: Me, Who has access: Anyone).
- When you modify the Apps Script code, redeploy as a new version and update MCP_WEB_APPS_URL accordingly.
- If you encounter authentication issues, verify GEMINI_API_KEY is valid and that the environment variables are exported in the shell/session running Gemini.
- The extension uses a Web App endpoint; latency may vary based on Google Apps Script execution time.
- You can customize environment variables per deployment if needed, but keep GEMINI_API_KEY and MCP_WEB_APPS_URL consistent with the Apps Script endpoint.
- If you need to update the MCP server prompt capabilities, refer to the ToolsForMCPServer project for supported commands and prompts.
Related MCP Servers
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
google_ads_mcp
The Google Ads MCP Server is an implementation of the Model Context Protocol (MCP) that enables Large Language Models (LLMs), such as Gemini, to interact directly with the Google Ads API.
ToolsForMCPServer
The Gemini CLI confirmed that the MCP server built with Google Apps Script (GAS), a low-code platform, offers immense possibilities. If you've created snippets for GAS, these could be revitalized and/or leveraged in new ways by using them as the MCP server. The Gemini CLI and other MCP clients will be useful in achieving this.
MCPApp
This text introduces the Model Context Protocol (MCP) for AI interaction, exploring Google Apps Script (GAS) as a server option. It shows feasibility with a sample but notes the lack of a GAS SDK, aiming to encourage understanding and development.
gemini-cli-gopls
This extension integrates the official MCP of the Go language server (gopls) with Gemini CLI.
SyberAgent
下一代PC本地自动化多智能体框架