Data, Privacy, and Security

• Scoped to your permissions. MCP tools use your authenticated Attentive credentials. Access depends on your account, the selected company, and authorization checks for the requested action.
• Limited to MCP tool activity. Attentive receives the tool calls, tool inputs, and tool results needed to fulfill the request. Attentive does not receive the full AI conversation transcript unless your AI application includes that content in tool inputs.
• Read and write access. Custom MCP connections default to read-only mode; tools that change Attentive data require ?readOnly=false. Native connectors manage their connection configuration and may include write tools.
• Sensitive subscriber data. list_segment_subscribers can return subscriber phone numbers, email addresses, names, and signup dates. This tool can be available in read-only sessions. Results are returned to your chosen AI application and may be processed or retained by that application’s AI provider depending on their policies.
• External AI providers. Tool inputs and results are returned to your chosen AI application and may be processed or retained by that application’s AI provider. Review that provider’s security, privacy, and retention policies before using personal or sensitive data.
• Human-in-the-loop. Attentive strongly recommends human review and approval for all write actions via the MCP.
• No credentials in config. Authentication uses OAuth through Attentive login. You do not need to enter an Attentive password or API key in your MCP configuration.

Note: Attentive logs operational security and diagnostic information for MCP usage, including authentication and session lifecycle events, write-tool metadata, and failures with error context. Normal successful tool outputs are not written to application logs by the tool registry.