Autonomous AI Agents & SDKs (LangChain, CrewAI, AutoGen)

Build custom autonomous agents, scheduled background workflows, and AI pipelines that interact with your WordPress site using Python or TypeScript.

Connecting with LangChain (Python)

Using the official mcp Python SDK and LangChain:

import asyncio
from mcp import ClientSession
from mcp.client.sse import sse_client
from langchain_anthropic import ChatAnthropic

async def main():
    async with sse_client("https://gateway.digentsmartai.com/api/mcp/YOUR_SITE_UUID") as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            
            # List available WordPress engines
            tools = await session.list_tools()
            print(f"Discovered {len(tools.tools)} WordPress operational engines:")
            for t in tools.tools:
                print(f" - {t.name}: {t.description}")
            
            # Invoke WordPress content creation tool
            result = await session.call_tool(
                "wp_content",
                arguments={
                    "action": "create",
                    "title": "Automated Market Intelligence Report 2026",
                    "content": "<!-- wp:paragraph --><p>Generated by autonomous Python pipeline.</p><!-- /wp:paragraph -->",
                    "status": "draft"
                }
            )
            print("Post created:", result.content)

asyncio.run(main())

CrewAI Multi-Agent Workflow Example

Define specialized agents where one conducts web research, one optimizes SEO, and one publishes directly to WordPress via Digent MCP tools:

from crewai import Agent, Task, Crew

publisher_agent = Agent(
    role="WordPress Webmaster Agent",
    goal="Publish high-quality articles with proper Gutenberg formatting and Rank Math SEO tags",
    backstory="You are an expert WordPress publisher equipped with Digent Smart AI MCP tools.",
    tools=[...], # Digent MCP tools mapped to CrewAI
    verbose=True
)