search_cases
AI agents call search_cases to retrieve information from SellerGuide MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches for cases, which is a retrieval operation with no side effects. It fits the Read category: queries data without modifying, deleting, or executing operations. Severity is low because the tool only accesses informational consulting content about SellerGuide services. Confidence is moderately high due to the naming convention and server context, but lowered slightly due to the missing description.
From the tool's definition Tool name 'search_cases' indicates a query/search operation. The sibling tools on this server (get_advantages, get_company_overview, list_cases, list_packages, list_services) are all informational reads.
Attacks that exploit this kind of access
search_cases. It is categorised as a Read tool in the SellerGuide MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SellerGuide MCP Server MCP server in PolicyLayer and add a rule for search_cases: 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 SellerGuide MCP Server. Nothing to install.
search_cases 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_cases 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_cases. 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_cases is provided by the SellerGuide MCP Server MCP server (kabanovmp/sellerguidemcp). 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 →