AI agents call dynamic.tool.list to retrieve information from Dynamic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates existing dynamic tools from local storage without creating, modifying, deleting, or executing anything. It is a pure read operation with minimal blast radius—an agent misusing it would only gain visibility into what tools are available, not the ability to invoke them or alter state. Severity is low because information disclosure of tool metadata poses minimal direct risk.
From the tool's definition Tool name 'dynamic.tool.list' and description 'List all dynamic tools currently registered in local storage' indicate a query operation with no side effects.
Attacks that exploit this kind of access
List all dynamic tools currently registered in local storage. It is categorised as a Read tool in the Dynamic MCP Server, which means it retrieves data without modifying state.
Register the Dynamic MCP server in PolicyLayer and add a rule for dynamic.tool.list: 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 Dynamic. Nothing to install.
dynamic.tool.list 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 dynamic.tool.list 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 dynamic.tool.list. 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.
dynamic.tool.list is provided by the Dynamic MCP server (mcpland/dynamic-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 →