Skip to main content
The Within MCP is read-mostly and scoped intentionally. Knowing where it stops keeps assistant behavior honest.

​
Read-only access

Workspace data tools available through the MCP are query-only. The optional submit_feedback tool sends user-approved feedback to Within analytics. You can search, read, explore, and analyze. You cannot create or modify processes, artifacts, or graph entities through the MCP — those writes happen in the Within UI.

​
Authentication coverage

OAuth is supported in Claude, ChatGPT, Claude Code (via the plugin), Codex (via codex mcp login), Cursor (via the Connect button on remote MCP servers), Gemini CLI (via /mcp auth), and Microsoft Copilot (via a custom Copilot Studio agent). For any client that doesn’t yet support MCP OAuth, use the API key fallback. See Authentication for the full breakdown.

​
Workspace scope

Each connection is scoped to one Within workspace. If the user belongs to multiple workspaces, they switch by reconnecting (OAuth) or by using a key generated in the other workspace (API key) — see Authentication → Switching workspaces.

​
Tool surface evolves

The production tool catalog grows over time as new Within capabilities ship (additional graph traversals, write tools for specific safe operations). The Tool reference is the live source of truth — check there before assuming a tool exists.

​
Agent Development Kit

  • Cowork runs Agent Recommendations, Future State Design, and Agent Design. Use Claude Code or Codex for Agent Build.
See Download and install.

​
When to fall back to the UI

  • Bulk edits to processes or artifacts.
  • Configuring workspace-level attributes or policies.
  • Inviting users or managing roles.
For everything else, the MCP should be enough — and if it isn’t, reach out.