Amplitude
The Amplitude agent connector is a Python package that equips AI agents to interact with Amplitude 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.
Connector for the Amplitude Analytics API. Provides access to core analytics data including event exports, cohort definitions, chart annotations, event type listings, active user counts, and average session length metrics. Authentication uses HTTP Basic with your Amplitude API key and secret key.
Example prompts
The Amplitude connector is optimized to handle prompts like these.
- List all chart annotations in Amplitude
- Show me all cohorts
- List all event types
- Which cohorts have more than 1000 users?
- What are the most popular event types by total count?
- Show me annotations created in the last month
Unsupported prompts
The Amplitude connector isn't currently able to handle prompts like these.
- Create a new annotation
- Delete a cohort
- Export raw event data
Entities and actions
This connector supports the following entities and actions. For more details, see this connector's full reference documentation.
| Entity | Actions |
|---|---|
| Annotations | List, Get, Context Store Search |
| Cohorts | List, Get, Context Store Search |
| Events List | List, Context Store Search |
| Active Users | List, Context Store Search |
| Average Session Length | List, Context Store Search |
Amplitude API docs
See the official Amplitude 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 AmplitudeConnector 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.amplitude import AmplitudeConnector
connector = connect("amplitude", workspace_name="<your_workspace_name>")
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@AmplitudeConnector.tool_utils
async def amplitude_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.amplitude import AmplitudeConnector
connector = connect("amplitude", workspace_name="<your_workspace_name>")
@tool
@AmplitudeConnector.tool_utils
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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.amplitude import AmplitudeConnector
connector = connect("amplitude", 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)
@AmplitudeConnector.tool_utils(framework="openai_agents")
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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="Amplitude Assistant", tools=[amplitude_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.amplitude import AmplitudeConnector
connector = connect("amplitude", workspace_name="<your_workspace_name>")
mcp = FastMCP("Amplitude Agent")
@mcp.tool
@AmplitudeConnector.tool_utils
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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.amplitude import AmplitudeConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = AmplitudeConnector(
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
@AmplitudeConnector.tool_utils
async def amplitude_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.amplitude import AmplitudeConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = AmplitudeConnector(
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
@AmplitudeConnector.tool_utils
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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.amplitude import AmplitudeConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = AmplitudeConnector(
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)
@AmplitudeConnector.tool_utils(framework="openai_agents")
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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="Amplitude Assistant", tools=[amplitude_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.amplitude import AmplitudeConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = AmplitudeConnector(
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("Amplitude Agent")
@mcp.tool
@AmplitudeConnector.tool_utils
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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.amplitude import AmplitudeConnector
from airbyte_agent_sdk.connectors.amplitude.models import AmplitudeAuthConfig
connector = AmplitudeConnector(
auth_config=AmplitudeAuthConfig(
api_key="<Your Amplitude project API key. Find it in Settings > Projects in your Amplitude account.
>",
secret_key="<Your Amplitude project secret key. Find it in Settings > Projects in your Amplitude account.
>"
)
)
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@AmplitudeConnector.tool_utils
async def amplitude_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.amplitude import AmplitudeConnector
from airbyte_agent_sdk.connectors.amplitude.models import AmplitudeAuthConfig
connector = AmplitudeConnector(
auth_config=AmplitudeAuthConfig(
api_key="<Your Amplitude project API key. Find it in Settings > Projects in your Amplitude account.
>",
secret_key="<Your Amplitude project secret key. Find it in Settings > Projects in your Amplitude account.
>"
)
)
@tool
@AmplitudeConnector.tool_utils
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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.amplitude import AmplitudeConnector
from airbyte_agent_sdk.connectors.amplitude.models import AmplitudeAuthConfig
connector = AmplitudeConnector(
auth_config=AmplitudeAuthConfig(
api_key="<Your Amplitude project API key. Find it in Settings > Projects in your Amplitude account.
>",
secret_key="<Your Amplitude project secret key. Find it in Settings > Projects in your Amplitude account.
>"
)
)
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@AmplitudeConnector.tool_utils(framework="openai_agents")
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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="Amplitude Assistant", tools=[amplitude_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.amplitude import AmplitudeConnector
from airbyte_agent_sdk.connectors.amplitude.models import AmplitudeAuthConfig
connector = AmplitudeConnector(
auth_config=AmplitudeAuthConfig(
api_key="<Your Amplitude project API key. Find it in Settings > Projects in your Amplitude account.
>",
secret_key="<Your Amplitude project secret key. Find it in Settings > Projects in your Amplitude account.
>"
)
)
mcp = FastMCP("Amplitude Agent")
@mcp.tool
@AmplitudeConnector.tool_utils
async def amplitude_execute(entity: str, action: str, params: dict | None = None):
"""Execute Amplitude 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: 1.0.3