How to integrate Agility cms MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Agility cms Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Agility cms to CrewAI using the Composio tool router. By the end, you'll have a working Agility cms agent that can list all authors for our blog, fetch content items tagged 'product-launch', show sitemap paths for the main website, get details of the 'about us' page through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Agility cms account through Composio's Agility cms MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Agility cms connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Agility cms
  • Build a conversational loop where your agent can execute Agility cms operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

What is the Agility cms MCP server, and what's possible with it?

The Agility cms MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Agility CMS account. It provides structured and secure access to your content models, pages, authors, categories, and more, so your agent can fetch content, retrieve metadata, manage sitemaps, and automate content discovery on your behalf.

  • Content item and list retrieval: Instantly fetch specific content items by ID or pull paginated lists by reference name, complete with filtering and sorting.
  • Dynamic schema and model insights: Allow your agent to get details on content models and page modules, so it can adapt to schema changes and build flexible digital experiences.
  • Page and sitemap management: Retrieve detailed information about pages—including metadata, content zones, and components—or pull the flat sitemap for custom routing and navigation logic.
  • Author, category, and tag lookup: Effortlessly list all authors, categories, and tags within your CMS instance to enable rich content filtering and assignment workflows.
  • Log and sync monitoring: Access recent sync logs to keep tabs on content updates and ensure your agent is always working with the latest data.

Supported Tools & Triggers

Tools
Get AuthorsTool to retrieve all authors from an agility cms instance.
Get CategoriesTool to get all categories.
Get Content ItemTool to fetch details of a content item by content id.
Get Content ListTool to retrieve a list of content items by reference name.
Get Content ModelsTool to retrieve content models and page modules.
Get LogsTool to retrieve sync items (logs) from agility cms.
Get PageTool to retrieve details of a page, including metadata, content zones, and components.
Get Page ModulesTool to retrieve all page modules defined in the agility instance.
Get Sitemap FlatTool to retrieve the flat sitemap as a mapping of page paths to sitemap items.
Get TagsTool to get all tags.
Sync Content ItemsTool to retrieve all content items in a paged format with sync tokens.
Sync PagesTool to retrieve all page items in paged format with sync tokens.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Agility cms connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Agility cms via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Agility cms MCP URL

Create a Composio Tool Router session for Agility cms

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["agility_cms"],
)
url = session.mcp.url
What's happening:
  • You create a Agility cms only session through Composio
  • Composio returns an MCP HTTP URL that exposes Agility cms tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Agility cms Assistant",
    goal="Help users interact with Agility cms through natural language commands",
    backstory=(
        "You are an expert assistant with access to Agility cms tools. "
        "You can perform various Agility cms operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Agility cms MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Agility cms operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Agility cms related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_agility_cms_agent.py

Complete Code

Here's the complete code to get you started with Agility cms and CrewAI:

python
# file: crewai_agility_cms_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Agility cms session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["agility_cms"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Agility cms assistant agent
    toolkit_agent = Agent(
        role="Agility cms Assistant",
        goal="Help users interact with Agility cms through natural language commands",
        backstory=(
            "You are an expert assistant with access to Agility cms tools. "
            "You can perform various Agility cms operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Agility cms operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Agility cms related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Agility cms through Composio's Tool Router. The agent can perform Agility cms operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Agility cms MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Agility cms MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Agility cms MCP with Claude Agent SDK

Google ADK

Google ADK

Use Agility cms MCP with Google ADK

LangChain

LangChain

Use Agility cms MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Agility cms MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Agility cms MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Agility cms MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Agility cms MCP?

With a standalone Agility cms MCP server, the agents and LLMs can only access a fixed set of Agility cms tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Agility cms and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Agility cms tools.

Can I manage the permissions and scopes for Agility cms while using Tool Router?

Yes, absolutely. You can configure which Agility cms scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Agility cms data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free