Search products by keyword; returns a short list of products.
AI agents call searchProducts to retrieve information from ZenTao MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves product data based on search criteria and returns results. It does not create, modify, delete, or execute any operations. This is a straightforward read operation typical of project management systems, with minimal security risk. Even if an agent performs excessive searches, the impact is limited to information disclosure of already-accessible product metadata.
From the tool's definition Tool name is 'searchProducts' and description states it 'Search products by keyword; returns a short list of products.' This is a query/search operation with no side effects.
Attacks that exploit this kind of access
Search products by keyword; returns a short list of products. It is categorised as a Read tool in the ZenTao MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ZenTao MCP Server MCP server in PolicyLayer and add a rule for searchProducts: 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 ZenTao MCP Server. Nothing to install.
searchProducts 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 searchProducts 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 searchProducts. 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.
searchProducts is provided by the ZenTao MCP Server MCP server (valiant-cat/zentao-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 →