AI agents use create_people_watchlist to create or update resources in Outx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outx environment.
This tool creates and stores a new watchlist configuration, which is a Write operation (reversible data creation). Severity is medium because creating watchlists could enable surveillance of individuals and data collection at scale, though the action itself is not destructive or irreversible.
From the tool's definition Tool explicitly performs 'Create a watchlist'—a persistent, reversible modification operation. The description confirms it 'monitors posts from specific LinkedIn profiles,' indicating data structure creation.
Attacks that exploit this kind of access
Create a watchlist that monitors posts from specific LinkedIn profiles. It is categorised as a Write tool in the Outx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Outx MCP server in PolicyLayer and add a rule for create_people_watchlist: 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 Outx. Nothing to install.
create_people_watchlist 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 create_people_watchlist 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 create_people_watchlist. 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.
create_people_watchlist is provided by the Outx MCP server (outx-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 →