AI agents call list_keyword_watchlists to retrieve information from Outx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing watchlist configurations. It performs a query operation to enumerate data belonging to the user's account without modifying, deleting, or executing any external actions. No data is created, modified, or destroyed. This is a straightforward Read operation with minimal security risk.
From the tool's definition Tool name is 'list_keyword_watchlists' and description states 'List all keyword watchlists for your account.' The verb 'list' and action of retrieving/enumerating existing watchlists indicates data retrieval with no side effects.
Attacks that exploit this kind of access
List all keyword watchlists for your account. It is categorised as a Read tool in the Outx MCP Server, which means it retrieves data without modifying state.
Register the Outx MCP server in PolicyLayer and add a rule for list_keyword_watchlists: 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.
list_keyword_watchlists 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 list_keyword_watchlists 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 list_keyword_watchlists. 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.
list_keyword_watchlists 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 →