Check if the user has interacted with the UI (clicks, inputs, etc). Returns the next interaction event or null if none.
AI agents call get_next_interaction to retrieve information from Claude Imagine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads user interaction data from the UI and returns it—it does not create, modify, delete, or execute operations. It is purely informational, making it a Read category risk. The severity is low because reading interaction events poses minimal risk; misuse would only retrieve user input data without causing damage or unexpected side effects.
From the tool's definition The tool 'get_next_interaction' checks and retrieves interaction events without modifying any data. The description states it 'Returns the next interaction event or null if none', which is a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
Check if the user has interacted with the UI (clicks, inputs, etc). Returns the next interaction event or null if none. It is categorised as a Read tool in the Claude Imagine MCP Server, which means it retrieves data without modifying state.
Register the Claude Imagine MCP server in PolicyLayer and add a rule for get_next_interaction: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Imagine. Nothing to install.
get_next_interaction is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_next_interaction rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_next_interaction. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_next_interaction is provided by the Claude Imagine MCP server (t3rm1nu55/claudeimagine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →