Slack MCP in Claude Code

Quick answer: Install the Slack MCP server with npx -y @modelcontextprotocol/server-slack, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on @modelcontextprotocol/server-slack as of April 15, 2026.

The Slack MCP server gives Claude Code a bot surface on a Slack workspace. Once connected, the model can list channels, read recent messages, post replies, search history, and fetch user profiles through the normal Slack Web API. The server is published as @modelcontextprotocol/server-slack and uses a bot token plus workspace ID for auth.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Slack server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Slack day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed: list_channels, post_message, reply_to_thread, add_reaction, get_channel_history, get_thread_replies, get_users, get_user_profile. Message posting is always as the bot, not as you; if you want messages to appear under your own name, use the user token variant with slightly different scopes and swap SLACK_BOT_TOKEN for SLACK_USER_TOKEN.

Prerequisites

A Slack workspace where you can install a custom app. A bot token with channels:history, channels:read, chat:write, and users:read scopes. The workspace team ID.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y @modelcontextprotocol/server-slack

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-slack"],
      "env": {
        "SLACK_BOT_TOKEN": "xoxb-XXX",
        "SLACK_TEAM_ID": "T01XXX"
      }
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• List the 10 most active channels in our workspace and tell me the purpose of each.
• Read the last 50 messages from #engineering and summarize the open technical discussions.
• Post a status update in #deploys saying that the 2.3.0 release is live, with a link to the GitHub release.
• Search for any messages in the last week mentioning the word outage and show me who posted them and in which channel.
• Get the profile info for user U01ABCDEF and tell me their title and time zone.
• Find every message in #support that references ticket number TKT-1234 and quote the most recent three.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

The bot token lives in SLACK_BOT_TOKEN and starts with xoxb-. The team ID in SLACK_TEAM_ID starts with T. Both must be kept out of committed files. Use your shell profile to export them and reference the variables from the Claude Code config. When you rotate the bot token at api.slack.com/apps, update the env var and restart Claude Code.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Tool calls return not_authed. The bot token is missing or wrong. Check the env var is set in the shell Claude Code was launched from. A quick echo $SLACK_BOT_TOKEN from the same terminal confirms.

Tool calls return missing_scope. The bot needs a scope the app was not granted. Open the app at api.slack.com/apps, add the scope under OAuth and Permissions, reinstall to workspace, and the new token picks up the scope.

Cannot read from a private channel. The bot must be a member of the channel. Invite the bot explicitly with /invite @your-bot-name from inside the channel, then retry the call.

Rate limited with ratelimited error. Slack tier 3 endpoints cap at 50 calls per minute per workspace. If Claude burns through that limit, back off for a minute and narrow the query to the specific channels you need.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Slack server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.