AI agents call lens_get_pending to retrieve information from Lens without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns existing annotation data without side effects. It is a read operation that retrieves information to display or process, similar to listing or fetching records. No data is created, modified, deleted, or executed. The blast radius is minimal — unauthorized access could expose annotations but cannot change system state or trigger external actions.
From the tool's definition Tool description states it 'Get[s] all pending annotations across all sessions' — a retrieval operation with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get all pending annotations across all sessions. Each annotation includes the project context if one was set. It is categorised as a Read tool in the Lens MCP Server, which means it retrieves data without modifying state.
Register the Lens MCP server in PolicyLayer and add a rule for lens_get_pending: 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 Lens. Nothing to install.
lens_get_pending 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 lens_get_pending 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 lens_get_pending. 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.
lens_get_pending is provided by the Lens MCP server (renderdraw/lens). 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 →