AI agents use dynamic.tool.create to create or update resources in Dynamic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dynamic environment.
This is a Write operation because it creates and registers new resources (dynamic tools) that persist in the system. While the tool itself doesn't execute arbitrary code directly, it enables registration of tools that may later be executed.
From the tool's definition Tool name explicitly states 'create' and description says 'Create and register a new dynamic tool'. The tool allows runtime creation of new tools that can be registered into the system.
Attacks that exploit this kind of access
Create and register a new dynamic tool. It is categorised as a Write tool in the Dynamic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dynamic MCP server in PolicyLayer and add a rule for dynamic.tool.create: 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.create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the dynamic.tool.create 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.create. 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.create 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 →