How to integrate Bunnycdn MCP with CrewAI

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Bunnycdn logo
CrewAI logo
divider

Introduction

This guide walks you through connecting Bunnycdn to CrewAI using the Composio tool router. By the end, you'll have a working Bunnycdn agent that can create a new pull zone for static assets, list all dns zones in your bunnycdn account, delete a storage zone by its id through natural language commands.

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

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

Also integrate Bunnycdn with

TL;DR

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

The Bunnycdn MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bunnycdn account. It provides structured and secure access to your CDN resources, so your agent can perform actions like managing storage zones, configuring DNS records, creating pull zones, and retrieving zone details on your behalf.

  • Effortless storage zone management: Instantly add or delete storage zones in specific regions, letting your agent optimize file storage based on your needs.
  • Automated DNS configuration: Direct your agent to create, update, or remove DNS records and zones, helping you keep your domain setup fast and flexible.
  • Pull zone creation and removal: Have your agent set up new pull zones or clean up unused ones, streamlining your content delivery workflows with minimal manual intervention.
  • Detailed configuration and status retrieval: Ask your agent to fetch comprehensive details for any DNS or pull zone, ensuring you always have up-to-date insights into your CDN setup.
  • Full account overview and auditing: Let the agent list all your DNS zones and pull critical stats, making it easy to audit or review your Bunnycdn resources on demand.

Supported Tools & Triggers

Tools
Add Allowed RefererAdds a hostname to the allowed referer list for a pull zone.
Add Blocked IPTool to add an IP address to the blocked list of a pull zone.
Add Blocked RefererTool to add a blocked referer to a pull zone.
Add Storage ZoneTool to add a new storage zone.
Add/Update Edge RuleTool to add or update edge rules in a BunnyCDN pull zone for advanced traffic control.
Check DNS Zone AvailabilityTool to check if a DNS zone name is available for registration.
Check Pull Zone AvailabilityTool to check if a pull zone name is available for registration.
Check Storage Zone AvailabilityTool to check if a storage zone name is available.
Create DatabaseCreates a new Bunny Database (SQLite-compatible edge database).
Create DNS RecordTool to create a new DNS record in a specific DNS zone.
Create Live Live 2Tool to retrieve live metrics data for database groups.
Create Pull ZoneCreates a new CDN pull zone in BunnyCDN for content delivery acceleration.
Create Shield Rate LimitTool to create a new Shield rate limit rule for protecting against excessive requests.
Create Shield Zone Access ListTool to create a new custom access list in a Shield Zone.
Delete Container RegistryTool to delete a container registry from Magic Containers.
Delete DatabaseTool to delete a BunnyCDN database by its ID.
Delete DNS RecordTool to delete a specific DNS record by its ID.
Delete DNS ZoneTool to delete a specific DNS zone by its ID.
Delete Edge RuleTool to delete an Edge Rule from a Pull Zone by its ID.
Delete Database GroupTool to delete a specific database group by its ID.
Delete Pull ZoneTool to delete a specific pull zone by its ID.
Delete Shield Zone Access ListTool to delete a custom access list from a Shield Zone.
Delete Storage ZoneTool to delete a storage zone.
Generate 2FA VerificationTool to generate 2FA verification details for account security setup.
Generate Database Auth TokenTool to generate an authentication token for a BunnyCDN database.
Get Billing SummaryTool to retrieve billing summary with data report for each Pull Zone.
Get Container Config SuggestionsTool to get AI-powered configuration suggestions for deploying a container image on BunnyCDN's Magic Containers platform.
Get Container Image DigestTool to retrieve the digest of a container image from a registry.
Get DatabaseTool to retrieve details of a specific database by its ID.
Get Database StatisticsTool to retrieve time-series statistics for a Bunny Database instance.
Get DNS Zone DetailsTool to retrieve details of a specific DNS zone by its ID.
Get DNS Zone ListTool to list all DNS zones in your Bunny CDN account.
Get Database GroupTool to retrieve details of a specific database group by its ID.
Get LanguagesTool to retrieve the list of languages supported by BunnyCDN's video library.
Get Database LimitsTool to retrieve current database limits for the authenticated BunnyCDN account.
Get oEmbedTool to retrieve oEmbed metadata for BunnyCDN video embeds.
Get Optimal Base RegionTool to get the optimal base region for Magic Containers.
Get Optimizer StatisticsRetrieve optimizer statistics for a Pull Zone to understand optimization performance.
Get Origin Shield Queue StatisticsTool to retrieve Origin Shield Queue Statistics for a specific Pull Zone.
Get Pull ZoneTool to retrieve details of a specific Pull Zone.
Get Pull Zone ListRetrieve a paginated list of all Pull Zones in your BunnyCDN account.
Get SafeHop StatisticsTool to retrieve SafeHop statistics for a specific Pull Zone.
Get Shield Bot Detection ConfigurationTool to retrieve bot detection configuration for a specific Shield Zone.
Get Shield DDoS EnumsTool to retrieve available enums for Shield DDoS configuration.
Get Shield Event LogsTool to retrieve Shield Event Logs for a specific Shield Zone and date.
Get Shield Metrics Bot DetectionTool to retrieve bot detection metrics for a specific Shield Zone.
Get Shield Metrics OverviewTool to retrieve comprehensive security metrics overview for a Shield Zone.
Get Shield Metrics Overview DetailedTool to retrieve detailed Shield zone metrics overview including DDoS protection, WAF, bot detection, rate limiting, access lists, and upload scanning statistics.
Get Shield Metrics Rate Limit by IDTool to retrieve shield metrics for a specific rate limit by ID.
Get Shield Metrics Rate LimitsTool to retrieve rate limit metrics for a Shield Zone.
Get Shield Metrics Upload ScanningTool to retrieve upload scanning metrics for a specific Shield Zone.
Get Shield Metrics WAF RuleTool to retrieve shield metrics for a specific WAF rule.
Get Shield Promo StateTool to retrieve a breakdown of Shield promotional data.
Get Shield Rate Limit by IDTool to retrieve a specific rate limit configuration by its ID.
Get Shield Rate LimitsTool to retrieve Shield Rate Limits for a specific Shield Zone.
Get Shield Shield ZonesTool to retrieve a list of all Shield Zones with their configurations.
Get Shield Upload Scanning ConfigurationTool to retrieve upload scanning configuration for a Shield Zone.
Get Shield WAF Custom Rule by IDTool to retrieve details of a specific Shield WAF custom rule by its ID.
Get Shield WAF Custom RulesTool to retrieve custom WAF rules for a specific Shield Zone.
Get Shield WAF Engine ConfigTool to retrieve Shield WAF engine configuration settings.
Get Shield WAF EnumsTool to retrieve available enums for Shield WAF configuration.
Get Shield WAF ProfilesTool to retrieve available WAF profiles for Shield zones.
Get Shield WAF Rules Plan SegmentationTool to retrieve WAF rules organized by subscription plan tiers.
Get Shield WAF Rules Review TriggeredTool to retrieve triggered WAF rules for review in a specific Shield Zone.
Get Shield WAF Rules by Shield Zone IDTool to retrieve Shield WAF Rules for a specific Shield Zone.
Get Shield ZoneTool to retrieve detailed configuration of a specific Shield Zone.
Get Shield Zone Access ListTool to retrieve a specific custom access list from a Shield Zone.
Get Shield Zone Access List EnumsTool to retrieve available enums for Shield Zone Access List configuration.
Get Shield Zone Access ListsTool to retrieve all access lists for a Shield Zone, including both managed threat lists and custom lists.
Get Shield Zone by Pull Zone IDTool to retrieve Shield Zone details by Pull Zone ID.
Get Shield Zones Pull Zone MappingTool to retrieve the mapping between Shield Zones and Pull Zones.
Get StatisticsTool to retrieve CDN statistics data for bandwidth, requests, cache performance, and geographic distribution.
Get Storage Zone DetailsTool to retrieve the full details of a storage zone, including configuration, usage metrics, and credentials.
Get Storage Zone ListTool to list all storage zones in your Bunny CDN account.
Get User Audit LogTool to retrieve user audit log entries for a specific date with optional filtering.
Get User DetailsTool to retrieve complete details of the currently authorized user account.
Get User LimitsTool to retrieve user limits and quotas for Magic Containers.
Get What's New ItemsTool to retrieve What's New items for the current user.
Invalidate Database Auth TokensTool to invalidate all authentication tokens for a BunnyCDN database.
Invalidate Group Auth TokensTool to invalidate authentication tokens for a specific database group.
List API KeysTool to retrieve a paginated list of all API keys in your BunnyCDN account.
List ApplicationsTool to list all Magic Container applications in your Bunny CDN account.
List Container Image TagsTool to list all available tags for a container image in a registry.
List Container RegistriesTool to list all container registries in your BunnyCDN Magic Containers account.
List Country ListTool to retrieve the list of countries supported by BunnyCDN with their tax rates and Points of Presence.
List Database Active UsageTool to retrieve active database usage statistics.
List Database ConfigurationTool to retrieve database configuration including available storage regions, primary regions, and replica regions.
List Databases V2Tool to list databases with pagination support using the v2 API.
List Database UsageTool to retrieve aggregated usage metrics for a Bunny Database instance.
List Database VersionsTool to list all versions of a specific database.
List Edge ScriptsRetrieve a paginated list of all edge scripts in your BunnyCDN account.
List Database GroupsTool to retrieve a list of all database groups in your BunnyCDN account.
List Group StatisticsTool to retrieve time-series statistics for a database group.
List Database Group UsageTool to retrieve aggregated usage statistics for a database group over a specified time period.
List NodesTool to retrieve a list of Magic Container nodes in your BunnyCDN account.
List NotificationsTool to list all notifications for the currently logged in user.
List Region ListTool to retrieve the list of regions supported by BunnyCDN with their geographic coordinates and pricing.
List RegionsTool to list all available regions for Magic Containers.
List Video LibrariesRetrieve a paginated list of all video libraries in your BunnyCDN account.
List VolumesTool to list all volumes for a Magic Container application in your BunnyCDN account.
Post Shield WAF Rules Review TriggeredTool to review and apply actions to triggered WAF rules in a specific Shield Zone.
Purge Pull ZonePurges the entire CDN cache for a specified pull zone.
Purge URLPurge a specific URL from the BunnyCDN cache to force it to be refreshed from the origin.
Remove Allowed RefererRemoves a hostname from the allowed referer list for a pull zone.
Remove Blocked IPTool to remove an IP address from the blocked list of a pull zone.
Remove Blocked RefererTool to remove a blocked referer from a pull zone.
Reset Pull Zone Security KeyTool to reset the security token key for a specific pull zone.
Reset What's NewTool to reset the What's New notification list for the current user.
Restore DatabaseTool to restore a BunnyCDN database to a specific generation/version.
Search Global SearchPerform a global search across all BunnyCDN resources (pull zones, storage zones, DNS zones, scripts, streams).
Search Public Container ImagesTool to search for public container images by prefix in a registry.
Set Edge Rule EnabledTool to enable or disable an edge rule in a BunnyCDN pull zone.
Set Force SSLTool to set Force SSL on a pull zone hostname.
Set Notifications OpenedTool to mark all user notifications as opened.
Update DatabaseTool to update an existing Bunny Database.
Update Database GroupTool to update a database group by its ID.
Update Pull ZoneTool to update settings for a specific pull zone.
Update Shield Bot Detection ConfigurationTool to update bot detection configuration for a specific Shield Zone.
Update Shield Rate Limit by IDTool to update a specific rate limit configuration by its ID.
Update Shield ZoneTool to update configuration settings for a Shield Zone.
Update Shield Zone Access ListTool to update a custom access list in a Shield Zone.
Update Shield Zone Access List ConfigurationTool to update an access list configuration in a Shield Zone.
Update Shield Zone Upload ScanningTool to update upload scanning settings for a shield zone.
Update Storage ZoneTool to update settings for a specific storage zone.
Update User DetailsTool to update the currently authorized user's account details.
Validate Origin URL Pull ZoneTool to validate an origin URL before creating or configuring a pull zone.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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 Bunnycdn 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[mcp] python-dotenv
What's happening:
  • composio connects your agent to Bunnycdn via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools[mcp] 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
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")
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 Bunnycdn MCP URL

Create a Composio Tool Router session for Bunnycdn

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["bunnycdn"])

url = session.mcp.url
What's happening:
  • You create a Bunnycdn only session through Composio
  • Composio returns an MCP HTTP URL that exposes Bunnycdn tools

Initialize the MCP Server

python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
What's Happening:
  • Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
  • MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
  • Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
  • Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
  • Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.

Create a CLI Chatloop and define the Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\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"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[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:
  • Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
  • Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
  • Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
  • Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
  • Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
  • Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.

Complete Code

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

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["bunnycdn"],
)
url = session.mcp.url

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

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end.\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"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

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

Conclusion

You now have a CrewAI agent connected to Bunnycdn through Composio's Tool Router. The agent can perform Bunnycdn 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 Bunnycdn MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Bunnycdn MCP?

With a standalone Bunnycdn MCP server, the agents and LLMs can only access a fixed set of Bunnycdn tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Bunnycdn 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 Bunnycdn tools.

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

Yes, absolutely. You can configure which Bunnycdn 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 Bunnycdn data and credentials are handled as safely as possible.

Used by agents from

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