AI agents call dynamic.tool.get 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.
The tool retrieves or queries data (a tool definition) with no side effects. It does not create, modify, execute, or delete resources. Even though the server has powerful Execute and Destructive sibling tools (sandbox.exec, dynamic.tool.delete), this specific tool is purely read-only and poses minimal risk if misused by an AI agent—worst case it returns information already stored in the system.
From the tool's definition 'Get one dynamic tool definition by name' — this is a retrieval operation that queries metadata about a tool without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Get one dynamic tool definition by name. 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.get: 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.get 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.get 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.get. 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.get 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 →