AgentChat MCP
An MCP tool that integrates mathematical computation with Gmail sending.
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: AgentChat MCP. It is used for: An MCP tool that integrates mathematical computation with Gmail sending. Full Skill content: https://321skill.com/skills/agentchat-mcp/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
This Skill addresses a practical pain point for developers who need to combine mathematical calculations with email notifications. In daily development or data analysis, there is often a need to quickly perform mathematical operations (such as factorial, Fibonacci sequence, equation solving, etc.) and promptly send the results to colleagues or clients. Manual handling is not only inefficient but also prone to errors. This tool uses Gemini AI to understand natural language instructions, automatically performs the mathematical calculations, and calls the Gmail API to send emails, achieving an automated closed loop from 'computation' to 'notification'.
Usage is straightforward: you simply clone the repository, install dependencies, and configure your Gemini API key and Gmail OAuth 2.0 credentials in the .env file. Then, start the MCP server and run the client script. After that, you can use natural language instructions to have the AI perform mathematical calculations and send emails, for example: 'Calculate the sum of the first 50 Fibonacci numbers and send the result to team@example.com.' The tool will automatically decompose the task, call the math tools for processing, format the result, and invoke the Gmail API to send the email.
It is well-suited for teams or individuals who need to batch process mathematical operations and send results. This is especially true for AI application developers, data analysts, and backend engineers already using the MCP protocol who wish to quickly integrate mathematical computation and email functionality. For scenarios requiring frequent sending of mathematical analysis reports to clients, professors, or teams, this tool can significantly reduce the time spent on manual operations.
It is recommended to use this tool within an existing MCP server environment. Note that it primarily relies on Gemini AI for mathematical reasoning, so ensure a stable network connection and sufficient API quota. Additionally, configuring the Gmail API requires creating a project and enabling OAuth 2.0 in the Google Cloud Console beforehand, making it suitable for users with some development experience.
Key Features
Unlike general-purpose MCP clients (such as Claude's native MCP tools), AgentChat MCP comes pre-configured with a mathematical operations toolkit (factorial, Fibonacci, equation solving, etc.) and a complete Gmail authentication flow, enabling the full 'mathematical computation → email sending' pipeline without the need for additional Python coding.
Limitations
Requires a Python 3.x environment, configuration of a Gemini API key and Gmail OAuth 2.0 credentials, and currently only supports single-instance calculation and email sending; it does not support batch queuing or asynchronous large-scale email tasks.
FAQ
What API keys are required?
A Gemini API key (from Google AI Studio) and Gmail API client ID and client secret (from Google Cloud Console) are required.
How do I obtain Gmail API credentials?
Create a project in Google Cloud Console, enable the Gmail API, create OAuth 2.0 credentials, download the credentials file and save it as `credentials.json`. The script will then automatically open a browser for authorization when run.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/agentchat-mcp/raw/index.md to read the original Skill definition (Markdown format) for AgentChat MCP, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agentchat-mcp/raw/index.md