Slack MCP Server

Slack MCP Server

Run a Slack MCP Server that lets AI assistants read and send messages in your workspaces. This Actor stays online as a standby server, accepting Slack bot tokens and channel IDs per request so any MCP client can interact with your conversations without polling or webhooks.

Building a custom Slack integration for an AI assistant means managing OAuth, socket mode, and event subscriptions. This Actor runs a persistent Model Context Protocol server that connects directly to your Slack workspace using a bot token you provide with each request. Your AI tools can list channels, post messages, and fetch conversation history through a standard MCP interface, with no extra infrastructure to maintain.

Who uses it	What they scrape Slack for
AI application developers	Give their LLM agents the ability to read Slack channel history and post updates during automated workflows.
DevOps engineers	Let an AI assistant query incident channels and send status summaries without building a custom Slack app.
Internal tools teams	Connect a company knowledge bot to Slack so employees can ask questions and get answers in threads.

What it does

This Actor runs a standby MCP server that authenticates to Slack on each request and returns channel lists, message history, and sent-message confirmations as structured MCP tool responses.

• 🔌 Standby MCP server: The Actor runs continuously and accepts Slack credentials in each MCP request body, no restart needed.
• 💬 Channel listing: Returns public channel names and IDs so an AI can discover where to read or post.
• 📨 Message posting: Sends text into any channel the bot has access to, with optional thread replies.
• 📖 History reading: Fetches recent messages from a channel, including user, timestamp, and text.

Results export to CSV, JSON, Excel, or XML, or straight from the API.

What you can do with Slack data

🤖 Let an AI agent post daily standup summaries.

A DevOps engineer configures an MCP client to call the server each morning, fetch yesterday's messages from the team channel, and post an AI-generated summary back into the same channel.

📋 Build a support bot that reads and replies in Slack.

An internal tools team connects a customer-support AI to the MCP server so it can monitor a help channel, read questions, and post answers in threads using the bot token.

🔍 Search conversation history from an AI assistant.

An AI application developer sends a user query to an LLM that calls the MCP server to pull recent Slack messages from a project channel, then answers based on the real discussion.

Why choose this scraper

	What you get
No polling or webhooks	The MCP server is always available, so AI clients call it exactly when they need Slack data.
Per-request credentials	Send a different bot token for each workspace or environment without reconfiguring the Actor.
Standard MCP protocol	Works with any MCP-compatible client, including Claude Desktop, without custom glue code.

How it compares

No other Store actor targets Slack the same way, so the honest comparison is with the alternatives teams actually weigh.

	Slack MCP Server	Build it in-house	By hand
Setup	Run it now, zero config	Days of engineering	None, but hours per pull
When Slack changes	Maintained for you	You fix it	You re-learn the page
Proxies, retries, anti-bot	Built in	Your problem	Browser only
Output	Fixed JSON schema, CSV/Excel export	Whatever you build	Copy-paste
Cost	Pay per result	Engineering time	Analyst hours

Configure the run

Provide a Slack bot token and an optional default channel ID in the MCP request body. The server uses these to authenticate and scope every tool call. The Input tab lists every parameter.

Pricing

Pay-per-result: $0.005 per result collected. You pay only for the results written to your dataset.

Results collected	Approximate cost
100 results	$0.50
1,000 results	$5.00
10,000 results	$50.00

New Apify accounts start with $5 in free credit.

Free users

Free-plan runs return up to 10 results as a preview. Upgrade your Apify plan to collect up to 1,000,000 results per run.

Run it

1. Create a free Apify account with $5 in credit.
2. Open the Slack MCP Server.
3. Set your inputs and any filters, then click Start.
4. Export the results as CSV, Excel, JSON, or XML from the Dataset tab.

Run it programmatically through the Apify API (run-sync-get-dataset-items) or the ApifyClient for JavaScript and Python.

Use with AI agents (MCP)

Give an AI agent live access to Slack through the Model Context Protocol. Add the Actor to Claude, Cursor, or any MCP client:

$claude mcp add --transport http apify "https://mcp.apify.com?tools=parseforge/slack-mcp"

Then prompt it in plain language to run the scraper and read back the results.

Troubleshooting

Why am I getting an authentication error?

Check that your Slack bot token is valid and has not been revoked. Make sure you are sending it in the MCP request body under the correct key, and that the token has the required OAuth scopes.

Why does the channel list return empty?

The bot token may not have the channels:read scope, or the bot has not been invited to any public channels. Add the scope in your Slack app settings and invite the bot to the channels you need.

Why can't I post a message to a channel?

Confirm the bot has the chat:write scope and has been added to the target channel. If the channel is private, the bot also needs the groups:write scope and an explicit invite.

Why does the MCP client fail to connect?

Ensure the Actor is running and you are using the correct MCP endpoint URL. Check that your client supports the Model Context Protocol and that network rules allow outbound connections to Apify.

FAQ

Question	Answer
What is a Slack MCP Server?	It is a server that implements the Model Context Protocol and exposes Slack actions like listing channels, reading messages, and posting messages as tools that AI models can call. This Actor runs that server for you on Apify.
Do I need to create a Slack app?	Yes, you need a Slack app with a bot token that has the necessary scopes (channels:history, channels:read, chat:write). You provide that token in each MCP request body.
How do I connect my AI client to this server?	Use any MCP-compatible client. Point it to the Actor's MCP endpoint URL and include your Slack bot token and optional default channel ID in the request body.
Can I use this with multiple Slack workspaces?	Yes. Send a different bot token in each MCP request, and the server will authenticate against the corresponding workspace for that call.
Does the Actor store my Slack messages?	The Actor does not persist message content between requests. It fetches and returns data only when an MCP client calls a tool, and the data is passed directly back to the client.
What scopes does my Slack bot token need?	At minimum, channels:history, channels:read, and chat:write. Add more scopes if you want the bot to access private channels or perform other actions.
Can I post threaded replies?	Yes, the message posting tool accepts a thread timestamp so the AI can reply directly in a thread.
Is there a rate limit?	The server respects Slack's API rate limits. If you hit a limit, the tool will return an error and the client can retry after the indicated delay.

Related actors

Browse the full ParseForge collection for more scrapers.

🆘 Need help? Email parseforge@protonmail.com with your run ID, your input, and what you expected.

⚠️ Disclaimer. This Actor is unofficial and is not affiliated with, endorsed by, or sponsored by Slack Technologies, LLC. It collects only publicly available data. You are responsible for using the collected data in compliance with the source's terms of service and applicable data-protection laws, including GDPR, CCPA, and PIPL. Do not use it to collect personal data unlawfully.