How to Connect Slack to Gemini — via MCP

There is no ready-made AnythingMCP connector for Slack yet. Slack is not in the AnythingMCP connector catalog, on Cloud or self-hosted. This guide covers what works today: Slack's own MCP offering, or importing the Slack REST API into AnythingMCP yourself and connecting it to Gemini.

Slack + Gemini

Slack's own MCP server

Slack runs an official MCP server at https://mcp.slack.com/mcp. It is open to approved clients (Slack lists Claude.ai, Claude Code, Perplexity and Cursor) and to Slack apps that are internal to your workspace or published in the Slack Marketplace; a workspace admin approves the connection. See Slack's MCP docs.

Step 1 — Get Slack credentials

Create a Slack app at api.slack.com/apps, add the bot token scopes the AI needs (for example channels:read, channels:history, chat:write), install the app to your workspace and copy the Bot User OAuth Token (xoxb-…). Invite the bot to the channels it should read.

Step 2 — Import the Slack API into AnythingMCP

Sign in to AnythingMCP Cloud (7-day free trial) or run your own instance with Docker:

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

1. Go to Connectors → Add Connector and choose REST API.
2. Enter https://slack.com/api as the Base URL.
3. Under Authentication, choose Bearer Token and paste the bot token.
4. Create the connector, then import the endpoints you need on its page as cURL Command (Slack's API reference has an example for each), or add tools by hand.
5. Under MCP Servers, open your server and switch the new connector on.

Slack's OpenAPI file for the Web API was archived in 2021, so add the methods you need by cURL: each Web API method is a call to https://slack.com/api/<method>, and Slack's method pages list its parameters.

What you can expose once it's imported

The tools depend on the endpoints you import. For example:

• Post a message to a channel (chat.postMessage)
• Read the recent messages of a channel (conversations.history)
• List channels (conversations.list)
• Look up a user (users.info)

Step 3 — Add the connector in Gemini

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Gemini CLI reads MCP servers from ~/.gemini/settings.json (on Windows %USERPROFILE%\.gemini\settings.json). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart gemini.
3. Run /mcp inside Gemini CLI (or gemini mcp list in your shell) — anythingmcp should show as connected.
4. Start prompting — Gemini CLI can now call the Slack tools you imported.

Self-hosting? Use your own instance's address instead of https://cloud.anythingmcp.com.

FAQ

Is there a ready-made Slack connector in AnythingMCP? Not yet. Slack is not in the connector catalog, so there is nothing to install in one click: import its API as shown above, or use Slack's own MCP offering if it covers what you need.

Where does Gemini CLI look for MCP servers? In ~/.gemini/settings.json for your user, or in .gemini/settings.json inside a project. gemini mcp list shows each server and whether it connects.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Meta Muse