Search across collections. Available: ${collections.join(
AI agents call search-dynamic to retrieve information from NestJS MCP Server Module without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Searching collections is a read-only operation that queries existing data without side effects. No data is created, modified, or deleted. The severity is low because search operations have minimal blast radius; even if an AI misuses them, the worst outcome is information disclosure or resource exhaustion, not data loss or financial impact.
From the tool's definition Tool name 'search-dynamic' and description indicate it 'Search[es] across collections' — a data retrieval operation with no modification or deletion capability.
Attacks that exploit this kind of access
Search across collections. Available: ${collections.join(. It is categorised as a Read tool in the NestJS MCP Server Module MCP Server, which means it retrieves data without modifying state.
Register the NestJS MCP Server Module MCP server in PolicyLayer and add a rule for search-dynamic: 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 NestJS MCP Server Module. Nothing to install.
search-dynamic 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-dynamic 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-dynamic. 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-dynamic is provided by the NestJS MCP Server Module MCP server (rekog-labs/mcp-nest). 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 →