What it does

Searches messages, threads, and channel metadata in a Slack workspace, and can post when given a token with write scope. The search half is immediately useful; the posting half deserves a human checkpoint. Start read-only and add the write scope only after you trust the output.

Install

Terminal

npx -y slack-mcp-server

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "slack-workspaces": {
      "command": "npx",
      "args": [
        "-y",
        "slack-mcp-server"
      ]
    }
  }
}

Use it for

Searching channel history for a decision nobody wrote down

Skip it if

Posting on your behalf without a review step

When to use it

Reach for this when the task needs slack inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Slack MCP