Slack

This connector is optimized for AI agents. For the data replication connector, see Slack.

The Slack agent connector is a Python package that equips AI agents to interact with Slack 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.

Slack is a business communication platform that offers messaging, file sharing, and integrations with other tools. This connector provides read access to users, channels, channel members, channel messages, and threads for workspace analytics. It also supports write operations including sending, updating, deleting, and scheduling messages, sending ephemeral messages, creating and renaming channels, archiving channels, removing users from channels, setting channel topics and purposes, adding and removing reactions, pinning messages, adding bookmarks, and inviting users to channels.

Example prompts

The Slack connector is optimized to handle prompts like these.

• List all users in my Slack workspace
• Show me all public channels
• List members of a public channel
• Show me recent messages in a public channel
• Show me thread replies for a recent message
• List all channels I have access to
• Show me user details for a workspace member
• List channel members for a public channel
• Send a message to a channel saying 'Hello team!'
• Post a message in the general channel
• Update the most recent message in a channel
• Create a new public channel called 'project-updates'
• Create a private channel named 'team-internal'
• Rename a channel to 'new-channel-name'
• Set the topic for a channel to 'Daily standup notes'
• Update the purpose of a channel
• Add a thumbsup reaction to the latest message in a channel
• React with 🚀 to the latest message in a channel
• Reply to a recent thread with 'Thanks for the update!'
• Invite a user to a channel
• Add a team member to the #project-updates channel
• Send an ephemeral message to a user in a channel
• Whisper a private reminder to a user in #general
• Schedule a message in a channel for tomorrow at 9am
• Send a reminder to a channel at 5pm today
• Delete the bot's last message in a channel
• Remove the :thumbsup: reaction from a message
• Archive the #old-project channel
• Remove a user from the #team channel
• Pin the latest important message in a channel
• Add a bookmark link to a channel
• What messages were posted in channel {channel_id} last week?
• Show me the conversation history for channel {channel_id}
• Search for messages mentioning {keyword} in channel {channel_id}

Unsupported prompts

The Slack connector isn't currently able to handle prompts like these.

• Delete channel {channel_id}
• Create a new user in the workspace
• Update user profile information
• Unarchive a channel

Entities and actions

This connector supports the following entities and actions. For more details, see this connector's full reference documentation.

Entity	Actions
Users	List, Get, Context Store Search
Channels	List, Get, Create, Update, Context Store Search
Channel Messages	List, Context Store Search
Threads	List, Context Store Search
Messages	Create, Update, Delete
Channel Topics	Create
Channel Purposes	Create
Channel Invites	Create
Reactions	Create, Delete
Ephemeral Messages	Create
Scheduled Messages	Create
Channel Archives	Create
Channel Kicks	Create
Pins	Create
Bookmarks	Create

Slack API docs

See the official Slack 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 SlackConnector and reads AIRBYTE_CLIENT_ID / AIRBYTE_CLIENT_SECRET from the environment:

Pydantic AI

Pydantic AI

from pydantic_ai import Agent
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.slack import SlackConnector

connector = connect("slack", workspace_name="<your_workspace_name>")

agent = Agent("openai:gpt-4o")

@agent.tool_plain
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

LangChain

LangChain

from langchain_core.tools import tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.slack import SlackConnector

connector = connect("slack", workspace_name="<your_workspace_name>")

@tool
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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

OpenAI Agents

from agents import Agent, function_tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.slack import SlackConnector

connector = connect("slack", 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)
@SlackConnector.tool_utils(framework="openai_agents")
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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="Slack Assistant", tools=[slack_execute])

FastMCP

FastMCP

from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.slack import SlackConnector

connector = connect("slack", workspace_name="<your_workspace_name>")

mcp = FastMCP("Slack Agent")

@mcp.tool
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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

Pydantic AI

from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.slack import SlackConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = SlackConnector(
    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
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

LangChain

LangChain

from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.slack import SlackConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = SlackConnector(
    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
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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

OpenAI Agents

from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.slack import SlackConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = SlackConnector(
    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)
@SlackConnector.tool_utils(framework="openai_agents")
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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="Slack Assistant", tools=[slack_execute])

FastMCP

FastMCP

from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.slack import SlackConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = SlackConnector(
    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("Slack Agent")

@mcp.tool
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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

Pydantic AI

from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.slack import SlackConnector
from airbyte_agent_sdk.connectors.slack.models import SlackTokenAuthenticationAuthConfig

connector = SlackConnector(
    auth_config=SlackTokenAuthenticationAuthConfig(
        bot_key="<Your Slack Bot Key (xoxb-) or User Token (xoxp-)>"
    )
)

agent = Agent("openai:gpt-4o")

@agent.tool_plain
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

LangChain

LangChain

from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.slack import SlackConnector
from airbyte_agent_sdk.connectors.slack.models import SlackTokenAuthenticationAuthConfig

connector = SlackConnector(
    auth_config=SlackTokenAuthenticationAuthConfig(
        bot_key="<Your Slack Bot Key (xoxb-) or User Token (xoxp-)>"
    )
)

@tool
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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

OpenAI Agents

from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.slack import SlackConnector
from airbyte_agent_sdk.connectors.slack.models import SlackTokenAuthenticationAuthConfig

connector = SlackConnector(
    auth_config=SlackTokenAuthenticationAuthConfig(
        bot_key="<Your Slack Bot Key (xoxb-) or User Token (xoxp-)>"
    )
)

# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@SlackConnector.tool_utils(framework="openai_agents")
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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="Slack Assistant", tools=[slack_execute])

FastMCP

FastMCP

from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.slack import SlackConnector
from airbyte_agent_sdk.connectors.slack.models import SlackTokenAuthenticationAuthConfig

connector = SlackConnector(
    auth_config=SlackTokenAuthenticationAuthConfig(
        bot_key="<Your Slack Bot Key (xoxb-) or User Token (xoxp-)>"
    )
)

mcp = FastMCP("Slack Agent")

@mcp.tool
@SlackConnector.tool_utils
async def slack_execute(entity: str, action: str, params: dict | None = None):
    """Execute Slack 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: 0.1.21