AI agents call list_settings to retrieve information from Wiswa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or enumerate settings without modifying them. Listed alongside lookup_setting and search_settings—both typical Read operations for discovery—it fits the Read category. No side effects, destructive, financial, or execute operations are indicated. Low severity due to settings being typically informational and non-sensitive in this context.
From the tool's definition Tool name 'list_settings' combined with server description indicating 'settings discovery' suggests retrieval of configuration data. Sibling tools include 'lookup_setting' and 'search_settings', which are clearly Read operations.
Attacks that exploit this kind of access
list_settings. It is categorised as a Read tool in the Wiswa MCP Server, which means it retrieves data without modifying state.
Register the Wiswa MCP server in PolicyLayer and add a rule for list_settings: 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 Wiswa. Nothing to install.
list_settings 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_settings 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_settings. 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_settings is provided by the Wiswa MCP server (tatsh/wiswa-mcp). 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 →