Configuration
Access Through Human Identity
Access Through Non-Human Identity
Autonomous Action Control
Connected Tools and Functions
Enterprise Retrieval Access
External Communication Access
Model and Build Provenance
Model Objective Alignment
Orchestrated AI System
Persistent Memory Access
Standing Instruction Stack
Vendor-Embedded AI
- ID: CF002.001
- Created: 26th August 2026
- Updated: 26th August 2026
- Contributor: James Weston
Unapproved Connected Tool
Unapproved connected tool occurs when a synthetic subject is configured to use a plugin, connector, function, application programming interface, or Model Context Protocol (MCP) server that has not been reviewed, approved, or inventoried.
This configuration creates an elevated exposure condition because an unapproved tool may introduce unknown permissions, data access, runtime behavior, supplier dependencies, or outbound destinations. The synthetic subject may treat the tool as trusted even though the organization has not assessed its provenance or purpose.
The primary risk is uncontrolled extension of capability. A single unapproved tool may allow the synthetic subject to retrieve data, send messages, call external services, or perform actions outside the intended design.
Investigators should review connected tool inventories, MCP server lists, configuration files, package manifests, marketplace installs, connector approvals, and tool-call logs. Particular attention should be given to tools installed outside approved channels or tools that do not appear in asset or vendor inventories.
Investigative Relevance
Unapproved connected tools are relevant because they expand what a synthetic subject can do without governance visibility. This sub-section is especially relevant where teams can install marketplace tools, local MCP servers, plugins, or connectors without central approval.