search-products
AI agents call search-products to retrieve information from Terminal Shop MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name and context clearly indicate this performs a search/query operation to retrieve product data. This is a Read operation with no capability to modify, create, or delete data. Severity is low as misuse would only expose product information already accessible through normal browsing.
From the tool's definition Tool name 'search-products' indicates a query operation that retrieves product information. The server description mentions 'browse products' as a capability, and search operations are non-destructive data retrieval with no side effects.
Attacks that exploit this kind of access
search-products. It is categorised as a Read tool in the Terminal Shop MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Terminal Shop MCP Server MCP server in PolicyLayer and add a rule for search-products: 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 Terminal Shop MCP Server. Nothing to install.
search-products 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-products 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-products. 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-products is provided by the Terminal Shop MCP Server MCP server (pashaydev/terminal.shop.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 →