MCP.so
Sign In

Multi-server MCP AI Agent

@IsaacDsouza

Repository

About Multi-server MCP AI Agent

Agentic AI platform that automates personal tasks by integrating with services such as Gmail, Notion, Slack, Zoom, and Google Drive via a modular tool marketplace. MCP, LangChain, MongoDB, Python

Config

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

{
  "mcpServers": {
    "mcp-with-multiple-servers": {
      "command": "uv",
      "args": [
        "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 Multi-server MCP AI Agent?

An MCP server that automates meetings, emails, and documents via natural language prompts. It integrates with the Google Gmail API and supports multiple MCP servers to orchestrate automation tasks.

How to use Multi-server MCP AI Agent?

Clone the repository, set up a Python virtual environment with uv, install dependencies, create a Google Cloud project and enable the Gmail API, generate OAuth 2.0 credentials, run the authentication process via npx, execute the token generator script, and finally run the application with uv run app.py.

Key features of Multi-server MCP AI Agent

  • Automates meetings, emails, and docs via prompts
  • Integrates multiple MCP servers for orchestration
  • Uses Google OAuth 2.0 for secure Gmail access
  • Local installation with Python virtual environment
  • Global credential storage in ~/.gmail-mcp/

Use cases of Multi-server MCP AI Agent

  • Automating email replies and summarization
  • Scheduling and managing meetings from prompts
  • Generating or updating documents via natural language
  • Chaining multiple MCP servers for complex workflows
  • Streamlining daily office tasks with AI agents

FAQ from Multi-server MCP AI Agent

What are the prerequisites for running this server?

You need Python (with uv installed), Node.js (for npx), and a Google Cloud project with the Gmail API enabled.

How do I obtain and set up OAuth credentials?

Create a Google Cloud project, enable the Gmail API, and generate an OAuth 2.0 client ID (desktop or web app). Download the JSON key file and rename it to gcp-oauth.keys.json.

Where are authentication credentials stored?

After authentication, credentials are saved globally in ~/.gmail-mcp/credentials.json. The OAuth key file can be placed in the current directory or ~/.gmail-mcp/.

What authentication methods are supported?

Both Desktop app and Web application OAuth credentials are supported. For web apps, add http://localhost:3000/oauth2callback to the authorized redirect URIs.

What is the token generator for?

The tokengen.py script (run with uv run tokengen.py) processes the OAuth credentials and generates tokens needed for the main application.

Frequently asked questions

What are the prerequisites for running this server?

You need Python (with uv installed), Node.js (for npx), and a Google Cloud project with the Gmail API enabled.

How do I obtain and set up OAuth credentials?

Create a Google Cloud project, enable the Gmail API, and generate an OAuth 2.0 client ID (desktop or web app). Download the JSON key file and rename it to `gcp-oauth.keys.json`.

Where are authentication credentials stored?

After authentication, credentials are saved globally in `~/.gmail-mcp/credentials.json`. The OAuth key file can be placed in the current directory or `~/.gmail-mcp/`.

What authentication methods are supported?

Both Desktop app and Web application OAuth credentials are supported. For web apps, add `http://localhost:3000/oauth2callback` to the authorized redirect URIs.

What is the token generator for?

The `tokengen.py` script (run with `uv run tokengen.py`) processes the OAuth credentials and generates tokens needed for the main application.

Comments

Basic information

Category

AI & Agents

Transports

stdio

Author

IsaacDsouza

More AI & Agents MCP servers

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

🔎 GPT Researcher

assafelovic

An autonomous agent that conducts deep research on any data using any LLM providers

28.1K

MCP Server - Remote MacOs Use

baryhuang

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

487

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