How do I get started with Slack MCP?

Subscribe, then create a Slack App at **api.slack.com/apps → Create New App**. Go to **OAuth & Permissions**, add the required bot scopes (channels:read, chat:write, search:read, users:read), install the app to your workspace, and paste the **Bot User OAuth Token** (starts with xoxb-) here. No code, no webhooks — just connect and go.

Can my AI agent send messages and reply in threads?

Yes. Your agent can post to any channel the bot has been invited to — including threaded replies. Just say 'post in #engineering that the deploy is complete' or 'reply in the thread about the bug fix'. It supports Slack's full mrkdwn formatting including bold, links, code blocks, and mentions.

How can I find a specific conversation from last week?

Tell your agent to search for it — 'find messages about the Q3 budget review' or 'search for messages from @sarah about the client proposal'. The agent uses Slack's search API with support for modifiers like from:user, in:channel, and date ranges. No more scrolling through channels — your agent retrieves the exact messages you need.

Can I manage multiple channels and monitor team activity?

Absolutely. List all channels to get an overview of your workspace structure, read history from specific channels to audit conversations, and check team member profiles, statuses, and timezones. Perfect for distributed teams, engineering organizations, and operations managers who need a bird's-eye view of communication across dozens of channels.

Slack MCP Server for OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: Slack
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Slack through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Slack Assistant",
            instructions=(
                "You help users interact with Slack. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Slack"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Slack MCP Server

Transform your team communication into an AI-powered workflow with Slack, the world's leading workplace messaging platform. Your agent becomes a direct participant in your Slack workspace — sending messages, searching across channels, and reacting to conversations without you ever switching tabs.

The OpenAI Agents SDK auto-discovers all 6 tools from Slack through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Slack, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Send Messages — Post messages to any channel or DM, including threaded replies, using Slack's rich mrkdwn formatting.
Search Conversations — Find messages across your entire workspace by keyword, sender, or channel using powerful search modifiers.
Browse Channels — List all available channels with their topics, purposes, and member counts to understand your workspace structure.
Read Channel History — Retrieve recent messages from any channel to catch up on conversations or audit activity.
Manage Users — List workspace members with their roles, emails, statuses, and timezones.
React to Messages — Add emoji reactions to specific messages for quick acknowledgments.

The Slack MCP Server exposes 6 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Slack to OpenAI Agents SDK via MCP

Follow these steps to integrate the Slack MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 6 tools from Slack

Why Use OpenAI Agents SDK with the Slack MCP Server

OpenAI Agents SDK provides unique advantages when paired with Slack through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Slack + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Slack MCP Server delivers measurable value.

Automated workflows: build agents that query Slack, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Slack, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Slack tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Slack to resolve tickets, look up records, and update statuses without human intervention

Slack MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect Slack to OpenAI Agents SDK via MCP:

channels_history

Requires the channel ID (use channels_list to find it). Returns messages in reverse chronological order. Get recent messages from a Slack channel

channels_list

Returns public and private channels the bot has access to. Channel IDs are needed for sending messages or reading history. List Slack channels in the workspace

messages_search

Searches message content, usernames, and channels. Results are sorted by most recent first. Search for messages across the Slack workspace

messages_send

Requires the channel ID. Use channels_list to find available channels. Optionally specify thread_ts to reply in a thread. Send a message to a Slack channel or DM

reactions_add

Requires the channel ID and the exact message timestamp (ts). Use channels_history to find message timestamps. Add a reaction emoji to a Slack message

users_list

Returns user IDs, names, emails, and status. User IDs are needed for sending DMs or identifying message authors. List users in the Slack workspace

Example Prompts for Slack in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Slack immediately.

"List all channels in my Slack workspace."

"Post a message in #engineering: 'Deploy v2.4.1 is live on production 🚀'"

"Search for messages about 'API outage' from last week."

Troubleshooting Slack MCP Server with OpenAI Agents SDK

Common issues when connecting Slack to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Slack + OpenAI Agents SDK FAQ

Common questions about integrating Slack MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.