MCP AI Agent

@Shilpaj1994

Repository

Basic information

About MCP AI Agent

AI Agent interacting with multiple MCP servers

#mathgpt #math-solver #math-assistant

MCP AI Agent config

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

{
  "mcpServers": {
    "MCP-AI-Agent": {
      "command": "python",
      "args": [
        "agent.py"
      ]
    }
  }
}

MCP AI Agent tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

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

Overview

What is MCP AI Agent?

MCP AI Agent is an intelligent agent that performs complex mathematical operations, creates visual presentations in Google Slides, and communicates results via Gmail. It showcases the integration of multiple Model Context Protocol servers working together to solve a compound task.

How to use MCP AI Agent?

Install dependencies with pip install -r requirements.txt, set up Google API credentials for Gmail and Slides, then run python agent.py. The system automatically calculates the Fibonacci sequence and exponentials, creates a slide with the result, saves it as a PNG, and sends it via email.

Key features of MCP AI Agent

Calculates Fibonacci sequences and performs exponential operations
Creates Google Slides presentations with text content
Downloads slides as PNG images
Sends emails with file attachments via Gmail
Manages email operations (read, trash, mark as read)
Handles Gmail API authentication

Use cases of MCP AI Agent

Automating multi-step workflows across different services
Generating visual reports from mathematical computations
Sending computed results as email attachments
Demonstrating MCP server integration for compound tasks

Frequently asked questions

What MCP servers does the system use?

The system uses three MCP servers: a Math server for calculations, a Slides server for Google Slides, and a Gmail server for email operations.

What are the prerequisites for running MCP AI Agent?

You need Python 3.8+, a Linux/Unix environment with X11 display server, and a Google account with access to Gmail and Google Slides.

How do I set up Google API access?

Create a project in Google Cloud Console, enable the Gmail API, create OAuth 2.0 credentials, and save them as `mcp_servers/credentials.json`. You may also set the `GMAIL_CREDS_FILE` and `GMAIL_TOKEN_FILE` environment variables.

Where are generated files saved?

Images are saved to `content/slide.png` in the project directory. You should use absolute paths when specifying file locations.

What should I do if Gmail authentication fails?

Delete the `token.json` file and rerun the agent. The first run will prompt you for Google account access.

Comments

More AI & Agents MCP servers

Agent Traffic Lab

ATL doesn’t just help agents find tools — it gets the job done. It finds and chooses the right AI provider, tool, or MCP server, executes the task, and switches to a fallback when a provider fails. It can optimize for lo

OpenZiti / LLM-Gateway

openziti

NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala

Gamedev Tavern

Gamedev Tavern is MCP for the game industry: studios, people, games and open quests. Have a goal — your AI agent writes a quest in your words and Tavern agents look for people and studios that fit. No goal — your agent i

Poly-Glot AI Workspace

hmoses

1,000+ fully localized prompt templates across 40+ categories. Compare Mode — send the same prompt to up to 9 AI providers (ChatGPT, Claude, Gemini, Grok, Groq, Copilot, Mistral, Perplexity, DuckDuckGo AI) and compare an

AskOne: Live Q&A and Polls

phuryn

Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the resu