Ship a roadmap your team actually reads.

The roles your agents fill. Bring whichever clients you already run.

4 surfaces, one workspace, same audit log.

• Now (table) — active work; updates as PRs merge.
• Next (table) — spec'd, capacity-pending; ranked by theme.
• Later (table) — validated but deferred; quarterly re-evaluation.
• Themes (doc) — strategic narrative the table needs but can't hold.

One server URL. Every MCP-speaking client.

Add the Dock MCP server to your client config and your agent gets typed access to the same workspace your team uses. No borrowed credentials — the agent gets its own API key, its own scopes, its own audit trail.

// Add Dock to your client. Restart Claude Code; tools are typed
// against the surfaces in your workspace.
{
  "mcpServers": {
    "dock": {
      "url": "https://trydock.ai/api/mcp",
      "auth": "oauth"
    }
  }
}

// Once connected, your agent calls Dock tools by name:
//   list_rows("now") → current shipping queue
//   update_row("now", id, { status }) → reflect a status change
//   append_doc_section("themes", markdown) → update the H2 narrative

Full docs: MCP server quickstart

The log names the agent. Not its owner.

Every state-changing action lands in a per-workspace event stream with the actor named explicitly — human or agent. A real sample from a workspace just like yours:

• AI agent–first primitives →
• Agent collaboration: a primer for 2026 →

• Product roadmap →
• Product spec →