AI agents use neptime_add_watch_later to create or update resources in Neptime — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Neptime environment.
This tool creates or modifies data reversibly by adding a video to a user's watch-later list. It is a Write operation because: (1) it persists new state (the video added to the list), (2) the action is reversible (the video can presumably be removed), and (3) it has no destructive or execute characteristics.
From the tool's definition Tool description states "Add a video to your watch later list" which creates/modifies user data (a watch-later collection). The Args show it takes a video_id and Returns a Confirmation, indicating successful data modification.
Attacks that exploit this kind of access
Add a video to your watch later list. Args: - video_id: Video ID to add (required) Returns: Confirmation. It is categorised as a Write tool in the Neptime MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Neptime MCP server in PolicyLayer and add a rule for neptime_add_watch_later: 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 Neptime. Nothing to install.
neptime_add_watch_later is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the neptime_add_watch_later 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 neptime_add_watch_later. 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.
neptime_add_watch_later is provided by the Neptime MCP server (neptime-mcp-server). 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 →