Data scope: AI Agents / MCP

Source: deck slides 10–11 · WPP Pilot assessment | Risks #2, #3, #6, #20

Legend: Today = Wrike capability | Confirm = setup/evidence | Pilot = proposed control | Gap = known shortfall. See the overview for all labels.

#2 Data Exposure & Scale#

Large-scale retrieval or updates.

Wrike AI Agents

• Today: An agent acts in selected folders or projects.
• Pilot: WPP approves those locations and checks how much data and work they contain.

Wrike MCP

• Confirm: Show which data the middleware lets MCP read or change, how much it can return, and whether bulk operations have enforced limits. Confirm WPP LLM client and/or MCP gateway can control which tools can be used.

#3 Permissions & Identity · #6 Process & Approval Bypass#

Privilege changes or rule bypass.

Wrike AI Agents

• Today: Agents cannot change access controls or approval rules.
• Pilot: Review the agent's configured actions before it is used in an approved location.

Wrike MCP

• Confirm: Test the user's Wrike access, the assistant's allowed tools and middleware restrictions together, including an action that should be denied.

#20 Autonomous Actions#

High-impact changes at scale.

Wrike AI Agents

• Pilot: Start with approved locations and use cases.
• Gap: A small location reduces exposure, but it is not an enforced record-count or request-rate cap.

Wrike MCP

• Confirm: MCP gateway behaves as expected in terms of action limits.

Screenshot in the deck (slide 11)#

Callout: "Configuring AI Agent location scope". Screenshot of the Agent scope section of the agent configuration, partly greyed out, with red outlines:

• Text: "Select which tasks, projects, or folders will define this agent's scope. The agent can watch for triggers and act only in these items and their subitems."
• A + Scope button that opens a menu with two entries, Task (submenu) and Project or folder (submenu).
• An info box partly hidden by the menu, ending "…now or anytime later from Space settings > AI agents."

Discussion log#