A comprehensive multi-agent system for interacting with Dev.to (DevTo) platform, built using Google ADK (Agent Development Kit) and Model Context Protocol (MCP). This project enables automated content creation, article management, and user profile interactions with DevTo through both Agent-to-Agent (A2A) communication and MCP server implementations.

This project implements a sophisticated agent architecture that can:

• Fetch and manage DevTo articles by tags or authors
• Generate and post markdown content to DevTo
• Retrieve user profiles and reading lists
• Manage article comments and followers
• Provide both SSE (Server-Sent Events) and STDIO interfaces for different integration needs

• Architecture Overview
• Project Structure
• Component Details
• Setup and Installation
• API Reference

The project follows a modular architecture with three main communication patterns:

┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   Client App    │───▶│  A2A Server     │───▶│   DevTo API     │
│   (main.py)     │    │ (devto_agent)   │    │                 │
└─────────────────┘    └─────────────────┘    └─────────────────┘
         │                       │                       ▲
         │                       ▼                       │
         │              ┌─────────────────┐              │
         └─────────────▶│   MCP Server    │──────────────┘
                        │ (SSE/STDIO)     │
                        └─────────────────┘

1. A2A Agent Server: High-level agent interface using Google ADK
2. MCP Servers: Low-level tool interface using Model Context Protocol
3. DevTo Service: Direct API integration with Dev.to
4. Tool Connectors: Bridge between agents and MCP servers

devto-agent/
├── a2a_servers/              # Agent-to-Agent server implementations
│   ├── agent_server/         # Individual agent definitions
│   │   ├── devto_agent.py   # Main DevTo agent server
│   │   ├── host_agent.py    # Host agent coordinator
│   │   └── utils.py         # Agent utilities
│   ├── agents/              # Agent base classes and implementations
│   │   ├── adk_agent.py     # Google ADK agent wrapper
│   │   └── utils/           # Agent utilities
│   └── common/              # Shared components
│       ├── client/          # A2A client implementations
│       ├── server/          # A2A server implementations
│       └── types.py         # Common type definitions
├── connector/               # Tool connectors
│   └── tools/
│       └── devto_tools.py   # DevTo MCP tool connector
├── mcp_servers/             # Model Context Protocol servers
│   ├── sse/                 # Server-Sent Events implementation
│   │   └── devto_server.py  # SSE-based MCP server
│   └── stdio/               # Standard I/O implementation
│       └── devto_server.py  # STDIO-based MCP server
├── services/                # Core business logic
│   └── devto_service.py     # DevTo API service wrapper
├── test/                    # Test files
├── main.py                  # Main client application
└── pyproject.toml          # Project dependencies

Purpose: Implements high-level agent interfaces using Google ADK framework.

• devto_agent.py: Main DevTo agent that handles:

  • Content generation for DevTo articles
  • Article fetching and management
  • User profile operations
  • Article posting with markdown support

• host_agent.py: Coordinator agent that can manage multiple sub-agents

• adk_agent.py: Wrapper class that integrates Google ADK with MCP tools

Purpose: Provides low-level tool interfaces using Model Context Protocol.

# Creates a Starlette web application with:
# - GET /sse: Server-Sent Events endpoint for real-time communication
# - POST /messages/: Message posting endpoint for client commands

Purpose: Direct integration with DevTo API.

class DevToService:
    def get_articles(page, per_page)           # Fetch paginated articles
    def get_articles_by_tag(tag)               # Filter by single tag
    def get_articles_by_tags(tags)             # Filter by multiple tags
    def get_article_content(article_id)        # Get full article content
    def post_article(title, body, tags)        # Create new article
    def get_user()                             # Current user info
    def get_user_articles()                    # User's articles
    def get_user_reading_list()                # User's saved articles
    def get_article_comments(article_id)       # Article comments

Purpose: Bridge between A2A agents and MCP servers.

• Establishes connection to MCP server
• Provides async tool interface for agents
• Handles connection lifecycle management

• Python 3.10 or higher
• UVicorn for running servers
• DevTo API key
• Google API key (for agent functionality)

1. Clone the repository:

   git clone https://github.com/HeetVekariya/devto-agent.git
   cd devto-agent

2. Environment Configuration: Create a .env file in the project root:

   DEVTO_API_KEY=your_devto_api_key_here
   DEVTO_BASE_URL=https://dev.to/api
   GOOGLE_API_KEY=your_google_api_key_here

3. Install Dependencies:

   uv pip install -e .

4. Start the Devto MCP Server

   uv run mcp_servers/sse/devto_server.py

5. Start Devto Agent

   uv run a2a_servers/agent_server/devto_agent.py

6. Start Host Agent:

   uv run a2a_servers/agent_server/host_agent.py 

7. Run the Client Application:

   uv run main.py

# Request:
"Retrieve my profile details"

# The agent response:
Here are your profile details:
{
  "type_of": "user",
  "id": ...,
  "username": "heetvekariya",
  "name": "HeetVekariya",
  "twitter_username": "heet_2104",
  "github_username": "HeetVekariya",
  "summary": "A Tech person doing Non-Tech things.",
  "location": "",
  "website_url": "https://heet-vekariya.vercel.app/",
  "joined_at": "Oct 12, 2023",
  "profile_image": "....jpeg"
}

# Request: 
"How many blogs I have published on devto ?"

# The agent response:
You have published 11 articles on Dev.to.

The DevTo agent provides these skills:

1. SKILL_DEVTO_CONTENT: Generate markdown content for DevTo articles
2. SKILL_DEVTO_ARTICLES: Fetch articles with or without tag filters
3. SKILL_DEVTO_USER_INFO: Retrieve user profiles and statistics
4. SKILL_POST_DEVTO_ARTICLE: Create and publish articles

Available through the MCP server:

• get_articles(page, per_page): Paginated article retrieval
• get_articles_by_tag(tag): Tag-based filtering
• get_article_content(article_id): Full article content
• post_article(title, body, tags): Article publishing
• get_user(): User profile information
• get_user_reading_list(): Saved articles