AI agents use create_ref to create or update resources in Substrate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Substrate environment.
This tool creates or updates references, which is a write operation that can be undone or modified later. It does not execute code, delete data irreversibly, or move money. The medium severity reflects that it modifies stored data and could impact system state if misused to create unwanted references, but the changes are not permanent or destructive.
From the tool's definition Tool description states 'Create or update a reference' — these are reversible write operations that modify data without permanent deletion.
Attacks that exploit this kind of access
Create or update a reference. It is categorised as a Write tool in the Substrate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Substrate MCP server in PolicyLayer and add a rule for create_ref: 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 Substrate. Nothing to install.
create_ref 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 create_ref 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 create_ref. 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.
create_ref is provided by the Substrate MCP server (ivan-saorin/substrate). 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 →