Mailchimp
The Mailchimp agent connector is a Python package that equips AI agents to interact with Mailchimp through strongly typed, well-documented tools. It's ready to use directly in your Python app, in an agent framework, or exposed through an MCP.
Mailchimp is an email marketing platform that enables businesses to create, send, and analyze email campaigns, manage subscriber lists, and automate marketing workflows. This connector provides read access to campaigns, lists, reports, email activity, automations, and more for marketing analytics and audience management.
Example prompts
The Mailchimp connector is optimized to handle prompts like these.
- List all subscribers in my main mailing list
- List all automation workflows in my account
- Show me all segments for my primary audience
- List all interest categories for my primary audience
- Show me email activity for a recent campaign
- Show me the performance report for a recent campaign
- Show me all my email campaigns from the last month
- What are the open rates for my recent campaigns?
- Who unsubscribed from list {list_id} this week?
- What tags are applied to my subscribers?
- How many subscribers do I have in each list?
- What are my top performing campaigns by click rate?
Unsupported prompts
The Mailchimp connector isn't currently able to handle prompts like these.
- Create a new email campaign
- Add a subscriber to my list
- Delete a campaign
- Update subscriber information
- Send a campaign now
- Create a new automation workflow
Entities and actions
This connector supports the following entities and actions. For more details, see this connector's full reference documentation.
| Entity | Actions |
|---|---|
| Campaigns | List, Get, Context Store Search |
| Lists | List, Get, Context Store Search |
| List Members | List, Get, Context Store Search |
| Reports | List, Get, Context Store Search |
| Email Activity | List, Context Store Search |
| Automations | List, Context Store Search |
| Tags | List, Context Store Search |
| Interest Categories | List, Get, Context Store Search |
| Interests | List, Get, Context Store Search |
| Segments | List, Get, Context Store Search |
| Segment Members | List, Context Store Search |
| Unsubscribes | List, Context Store Search |
Mailchimp API docs
See the official Mailchimp API reference.
SDK installation
uv pip install airbyte-agent-sdk
SDK usage
Connectors can run in hosted or open source mode.
Hosted
In hosted mode, API credentials are stored securely in Airbyte Agents. You provide your Airbyte credentials instead.
If your Airbyte client can access multiple organizations, also set organization_id.
This example assumes you've already authenticated your connector with Airbyte. See Authentication to learn more about authenticating. If you need a step-by-step guide, see the hosted execution tutorial.
The connect() factory returns a fully typed MailchimpConnector and reads AIRBYTE_CLIENT_ID / AIRBYTE_CLIENT_SECRET from the environment:
- Pydantic AI
- LangChain
- OpenAI Agents
- FastMCP
Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
connector = connect("mailchimp", workspace_name="<your_workspace_name>")
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
connector = connect("mailchimp", workspace_name="<your_workspace_name>")
@tool
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
# connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
connector = connect("mailchimp", workspace_name="<your_workspace_name>")
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@MailchimpConnector.tool_utils(framework="openai_agents")
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
agent = Agent(name="Mailchimp Assistant", tools=[mailchimp_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
connector = connect("mailchimp", workspace_name="<your_workspace_name>")
mcp = FastMCP("Mailchimp Agent")
@mcp.tool
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
Or pass credentials explicitly (equivalent, useful when you're not loading them from the environment):
- Pydantic AI
- LangChain
- OpenAI Agents
- FastMCP
Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = MailchimpConnector(
auth_config=AirbyteAuthConfig(
workspace_name="<your_workspace_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = MailchimpConnector(
auth_config=AirbyteAuthConfig(
workspace_name="<your_workspace_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
@tool
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
# connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = MailchimpConnector(
auth_config=AirbyteAuthConfig(
workspace_name="<your_workspace_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@MailchimpConnector.tool_utils(framework="openai_agents")
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
agent = Agent(name="Mailchimp Assistant", tools=[mailchimp_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = MailchimpConnector(
auth_config=AirbyteAuthConfig(
workspace_name="<your_workspace_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
mcp = FastMCP("Mailchimp Agent")
@mcp.tool
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
Open source
In open source mode, you provide API credentials directly to the connector.
- Pydantic AI
- LangChain
- OpenAI Agents
- FastMCP
Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
from airbyte_agent_sdk.connectors.mailchimp.models import MailchimpAuthConfig
connector = MailchimpConnector(
auth_config=MailchimpAuthConfig(
api_key="<Your Mailchimp API key. You can find this in your Mailchimp account under Account > Extras > API keys.>"
)
)
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
from airbyte_agent_sdk.connectors.mailchimp.models import MailchimpAuthConfig
connector = MailchimpConnector(
auth_config=MailchimpAuthConfig(
api_key="<Your Mailchimp API key. You can find this in your Mailchimp account under Account > Extras > API keys.>"
)
)
@tool
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
# connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
from airbyte_agent_sdk.connectors.mailchimp.models import MailchimpAuthConfig
connector = MailchimpConnector(
auth_config=MailchimpAuthConfig(
api_key="<Your Mailchimp API key. You can find this in your Mailchimp account under Account > Extras > API keys.>"
)
)
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@MailchimpConnector.tool_utils(framework="openai_agents")
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
agent = Agent(name="Mailchimp Assistant", tools=[mailchimp_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.mailchimp import MailchimpConnector
from airbyte_agent_sdk.connectors.mailchimp.models import MailchimpAuthConfig
connector = MailchimpConnector(
auth_config=MailchimpAuthConfig(
api_key="<Your Mailchimp API key. You can find this in your Mailchimp account under Account > Extras > API keys.>"
)
)
mcp = FastMCP("Mailchimp Agent")
@mcp.tool
@MailchimpConnector.tool_utils
async def mailchimp_execute(entity: str, action: str, params: dict | None = None):
"""Execute Mailchimp connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
Authentication
For all authentication options, see the connector's authentication documentation.
Version information
Connector version: 1.0.11