Skip to main content
Glama
deenesjakoruzh
googyaipro

Blogger Agent MCP

by googyaipro
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

🚀 Blogger Agent MCP & AI Content Generation Engine

Blogger Agent MCP is an autonomous multi-agent system based on Google Agent Development Kit (ADK) and Gemini 3.5 Flash, designed for deep trend analysis, live web search for up-to-date facts, automatic construction of multi-point travel routes in Google Maps, writing expert longreads, publishing documents in Google Docs, and distributing them via Gmail.

🌟 Key Features

  • 🧠 Multi-Agent Pipeline (Google ADK & Gemini 3.5 Flash): Use of specialized sub-agents BlogPlanner and BlogWriter under the control of a single orchestrator Root Agent.

  • 🌐 Live Web Search in Real Time (search_web): Grounding facts to the current date to prevent hallucinations and outdated LLM data.

  • 🗺 Grand Tour Router (get_scenic_travel_route): Building complex road trips Point A ➔ B ➔ C ➔ D with generation of clickable interactive maps in Google Maps.

  • 📈 Google Trends Integration: Automatic collection of rising key audience trends.

  • 🔒 Delegated OAuth 2.0 Authorization: Creating files directly on your personal Google Drive (Google Docs API) and sending messages from your personal Gmail (Gmail API).

  • ☁️ Cloud Native & Docker Ready: Ready for instant deployment on Google Cloud Run, Docker, and Dokploy.

Related MCP server: Universal Adapter

🏗 Pipeline Architecture

[Пользовательский Запрос]
        │
        ▼
[Root Agent (Blogger)]
        │
        ├──> 1. Trends Analysis (get_google_trends / pytrends)
        │
        ├──> 2. Live Web Search (search_web / DDGS Grounding)
        │
        ├──> 3. Scenic Route Planner (get_scenic_travel_route / Places & Routes API)
        │
        ├──> 4. Outline Generation (Sub-Agent: BlogPlanner)
        │
        ├──> 5. Full Article Generation (Sub-Agent: BlogWriter)
        │
        └──> 6. Export & Delivery
                 ├── Google Drive / Docs API (save_to_google_drive)
                 ├── Google Cloud Storage Backup (save_to_cloud_storage)
                 └── Gmail API Dispatch (send_article_email)

⚙️ Environment Variables (.env)

Create a .env file in the project root directory:

# Модель и регион Google Cloud Vertex AI
MODEL=gemini-3.5-flash
GOOGLE_CLOUD_LOCATION=global
GOOGLE_GENAI_USE_VERTEXAI=TRUE

# Ключ Google Maps Platform API
GOOGLE_MAPS_API_KEY=AIzaSyYourGoogleMapsApiKeyHere12345

# Хранилище Google Cloud Storage
GCS_BUCKET_NAME=your-gcs-bucket-name

# OAuth 2.0 Desktop Credentials (для личного Google Диска и Gmail)
OAUTH_CLIENT_ID=123456789012-yourclientid.apps.googleusercontent.com
OAUTH_CLIENT_SECRET=GOCSPX-yourClientSecretHere123456
OAUTH_REFRESH_TOKEN=1//04yourRefreshTokenHere_abcdefghijklmnopqrstuvwxyz

# Email для уведомлений
NOTIFICATION_EMAIL=your_email@gmail.com

📦 Quick Installation and Local Launch

1. Clone the Repository and Create venv

git clone https://github.com/your-username/bloggeragentmcp.git
cd bloggeragentmcp

python3 -m venv .venv
source .venv/bin/activate

2. Install Dependencies

pip install -r requirements.txt

3. OAuth 2.0 Authorization (One-Time Launch)

To obtain your long-lived OAUTH_REFRESH_TOKEN, run the authorization script:

python generate_oauth_token.py

Authorize in the opened browser under your Google account and copy the obtained refresh_token into .env.

4. Local Agent Launch

python agent.py

🐳 Deployment in Docker / Dokploy / Cloud Run

1. Launch via Docker Compose

Create docker-compose.yml:

version: '3.8'

services:
  blogger-agent:
    build: .
    container_name: blogger_agent
    restart: always
    ports:
      - "8080:8080"
    env_file:
      - .env

Run the container:

docker compose up -d

2. Deploy to Google Cloud Run

gcloud run deploy bloggeragentmcpv03 \
  --source . \
  --region us-east1 \
  --allow-unauthenticated \
  --set-secrets="OAUTH_REFRESH_TOKEN=oauth-refresh-token:latest" \
  --set-env-vars GOOGLE_GENAI_USE_VERTEXAI=TRUE,MODEL="gemini-3.5-flash",GOOGLE_CLOUD_LOCATION="global",GCS_BUCKET_NAME="your-gcs-bucket-name",NOTIFICATION_EMAIL="your_email@gmail.com"

3. Deploy to Dokploy

  1. Create an Application in the Dokploy panel.

  2. In Build Type, select Dockerfile.

  3. Fill in the variables in the Environment tab.

  4. Click Deploy.

📝 License

MIT License © 2026 Blogger Agent MCP Team.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers