> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Slack Context Provider

> Separate sub-agents under the hood keep scopes minimal: read agents never see `send_message`, and the write agent never sees history or search tools.

Separate sub-agents under the hood keep scopes minimal: read agents never see `send_message`, and the write agent never sees history or search tools. Uploads / downloads are off on both.

```python slack.py theme={null}
"""
Slack Context Provider
======================

SlackContextProvider exposes two tools to the calling agent:

- `query_<id>(question)` — read the workspace (search, channel
  history, threads, user / channel lookups)
- `update_<id>(instruction)` — post a message (resolves channel /
  user names, then calls `send_message` / `send_message_thread`)

Separate sub-agents under the hood keep scopes minimal: read agents
never see `send_message`, and the write agent never sees history or
search tools. Uploads / downloads are off on both.

This cookbook always runs the read prompt. If you set
`SLACK_WRITE_CHANNEL` (e.g. `SLACK_WRITE_CHANNEL=#agno-test`), it
also runs a write prompt that posts a hello message there. Without
it, posting is skipped so a casual `python cookbook/12_context/05_slack.py`
never spams a real channel.

Requires:
    OPENAI_API_KEY
    SLACK_BOT_TOKEN  (bot token; xoxb-...)
                     With scopes: channels:read, users:read; add
                     chat:write to exercise the write path.

    Optional:
    SLACK_TOKEN         (falls back here if SLACK_BOT_TOKEN isn't set)
    SLACK_USER_TOKEN    (user token; xoxp-...) for search_messages API
    SLACK_WRITE_CHANNEL (e.g. `#agno-test`) — opt in to the write demo
"""

from __future__ import annotations

import asyncio

from agno.agent import Agent
from agno.context.slack import SlackContextProvider
from agno.models.openai import OpenAIResponses

# ---------------------------------------------------------------------------
# Create the provider (token read from SLACK_BOT_TOKEN / SLACK_TOKEN)
# ---------------------------------------------------------------------------
slack = SlackContextProvider(model=OpenAIResponses(id="gpt-5.4-mini"))

# ---------------------------------------------------------------------------
# Create the Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5.4"),
    tools=slack.get_tools(),
    instructions=slack.instructions(),
    markdown=True,
)


async def main() -> None:
    print(f"\nslack.status() = {slack.status()}\n")

    # --- Read path (always runs) ---
    # CLI runs use bot-token-compatible channel history. Slack interface
    # runs include an action_token, so the provider can use assistant search.
    read_prompt = (
        "Find the 3 most recent messages in the #agents channel."
        "For each, author, and a one-line quote."
    )
    print(f"> {read_prompt}\n")
    await agent.aprint_response(read_prompt)

    # --- Write path (opt in via env) ---
    write_channel = "#agents"
    write_prompt = f"Post the message 'Hello from agno.context' to {write_channel}."
    print(f"\n> {write_prompt}\n")
    await agent.aprint_response(write_prompt)


if __name__ == "__main__":
    asyncio.run(main())
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      export SLACK_BOT_TOKEN="your_slack_bot_token_here"
      export SLACK_TOKEN="your_slack_token_here"
      export SLACK_USER_TOKEN="your_slack_user_token_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      $Env:SLACK_BOT_TOKEN="your_slack_bot_token_here"
      $Env:SLACK_TOKEN="your_slack_token_here"
      $Env:SLACK_USER_TOKEN="your_slack_user_token_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `slack.py`, then run:

    ```bash theme={null}
    python slack.py
    ```
  </Step>
</Steps>

Full source: [cookbook/12\_context/05\_slack.py](https://github.com/agno-agi/agno/blob/main/cookbook/12_context/05_slack.py)