AI agents call search_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.
A search function on a settings discovery server performs a read-only query operation with no apparent side effects. Even with an empty description, the tool name and contextual consistency with sibling read-only tools (get_defaults, list_settings, lookup_setting) strongly indicate this is a data retrieval mechanism. No modification, execution, deletion, or financial impact is suggested.
From the tool's definition Tool name 'search_settings' combined with sibling tools 'list_settings' and 'lookup_setting' indicates data retrieval operations. The empty description limits specificity, but the name pattern and server context (settings discovery) suggest a query operation.
Attacks that exploit this kind of access
search_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 search_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.
search_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 search_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 search_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.
search_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 →