Connector Β· Team messaging platform

Slack MCP Server & Agent Skill

Last updated

ibl.ai publishes a free Slack agent skill: a SKILL.md that teaches an AI agent to read and write Slack data and expose it as an MCP tool. Download it, connect your own Slack credentials, and run the agent on ibl.ai Agentic OS, where you own all the code and the data.

Slack holds a workspace's channels, direct messages, threads, files, canvases, lists and member profiles.

What is the Slack API, and what can an agent read from it?

HTTP methods named by object.action (conversations.history, chat.postMessage) for reading channel history, posting and scheduling messages, searching, managing users, files, canvases and lists.

  • API: Slack Web API (REST)
  • Access: Public, self-serve
  • Base URL: https://slack.com/api/{method}
  • Authentication: OAuth 2.0 (OAuth v2 install); Bot token (xoxb); User token (xoxp); App-level token (xapp)

Create a Slack app, request OAuth scopes and install it to a workspace. New commercial apps not approved for the Slack Marketplace get reduced conversations.history limits.

OAuth v2 install returns tokens. Bot tokens act as the app with granular scopes and survive the installer leaving; user tokens act as a member with that member's access. App-level tokens cover the app across an organization.

What can an agent read from Slack?

  • Channel history β€” GET conversations.history; scopes channels:history, groups:history, im:history, mpim:history. Tier 3.
  • Threads β€” conversations.replies returns the messages in a thread.
  • Search β€” Search messages, files, users and channels (available as tools on the Slack MCP server).
  • Users and members β€” Fetch user profiles and channel member lists.

What can an agent write to Slack?

  • Post message β€” POST chat.postMessage with chat:write; thread_ts posts a reply. About 1 message per second per channel. Confirm with the user first.
  • Schedule or draft message β€” Schedule messages or create drafts (Slack MCP server tools). Confirm with the user first.
  • Canvases β€” Create, read and update canvases.
  • Files β€” Upload files to channels. Confirm with the user first.

Limits: Tiered per method per workspace: Tier 1 1+/min, Tier 2 20+/min, Tier 3 50+/min, Tier 4 100+/min. Posting about 1 message/second per channel. 429 with Retry-After. New non-Marketplace apps: conversations.history 1 request/min, 15 objects.

Messages and files hold confidential business communications and personal data; channels may contain regulated content depending on the organization.

How do I connect Slack to an AI agent over MCP?

Slack publishes an official MCP server: Slack MCP server.

Slack-hosted at https://mcp.slack.com/mcp, generally available, OAuth with user tokens. Only directory-published or internal apps may use it; Web API rate limits apply.

You can register that server on ibl.ai as it is, or use the SKILL.md below when you want the agent to call the Slack Web API directly.

On ibl.ai an MCP connection is three records, and a working integration always needs all three:

  1. Register the server β€” POST …/mcp-servers/ with its URL, a transport (sse, websocket or streamable_http) and an auth_type of none, token or oauth2.
  2. Create a connection that holds the credential, scoped to the whole organization (platform), to a single agent, or to each user (user).
  3. Enable it on the agent β€” mcp-tool in tool_slugs and the server id in mcp_servers. Both lists are replaced, not merged, so read the settings first.

For an API key or a service credential, one token connection at platform scope serves the whole organization; scope a connection to a single agent when that agent needs narrower access than the rest.

The field reference is in MCP server connections, and the /iblai-api-agent-mcp skill runs all three steps from a coding agent.

What does the Slack agent skill do?

The Slack skill is one SKILL.md file named iblai-connect-slack. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails.

Download the Slack SKILL.md

Save it as .claude/skills/iblai-connect-slack/SKILL.md, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install:

$ npx skills add iblai/vibe --all

This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository.

It was checked against Slack's documentation on October 20, 2026. Test it against your own Slack setup before you rely on it.

What can I ask a Slack agent to do?

  • β€œSummarize what was decided in #launch-planning this week”
  • β€œFind the thread where we discussed the Q3 pricing change and link it”
  • β€œPost a status update to #eng-standup with today's open incidents”
  • β€œWho on the support team mentioned the SSO outage yesterday?”

How do I run a Slack agent on ibl.ai?

Agentic OS is where the agent runs on ibl.ai: it holds the Slack MCP connection, the model the agent uses, its instructions and its conversation history.

On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing β€” so you can deploy anywhere, from your own cloud to a fully air-gapped network.

Which ibl.ai agents work with Slack data?

Which ibl.ai platform skills does a Slack agent use?

  • /iblai-api-agent-mcp β€” MCP connectors for ibl.ai agents, end to end
  • /iblai-vibe-agent-mcp β€” Add the agent MCP tab (Model Context Protocol connector management with featured connectors, custom connectors, OAuth,…
  • /iblai-api-agent-tool β€” Enable or disable an ibl.ai agent's tools via the platform API

What else should I know before connecting Slack to an AI agent?

Is there an official Slack MCP server?

Yes. Slack publishes Slack MCP server.

You can register it on ibl.ai as an MCP server, or use the SKILL.md when you want the agent to call the Slack Web API directly.

Who can get Slack API credentials?

Create a Slack app, request OAuth scopes and install it to a workspace. New commercial apps not approved for the Slack Marketplace get reduced conversations.history limits.

Does Slack data leave my infrastructure when an ibl.ai agent uses it?

On ibl.ai, you own all the code and the data. Self-hosted in your cloud or data center, the agent, its MCP connections and its conversation logs stay inside your perimeter.

Because the platform is model-agnostic, you can point the agent at a model you host, so Slack records need not reach a third-party model provider.

Is the Slack agent skill free to use?

Yes. The SKILL.md is a free download with no sign-up. It assumes you already have Slack credentials, and your agreement with Slack still governs how you use its API.

Which other data sources can an AI agent connect to alongside Slack?

Which other Enterprise systems have a connector?

Every connector, grouped by sector, is on the connectors hub.