AI agents call list_refs to retrieve information from Substrate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a list of references, which is a classic read operation. The optional prefix filter is a typical query parameter for narrowing results. There are no indicators of data modification, deletion, or code execution. The blast radius is minimal—it only retrieves information already accessible to the user.
From the tool's definition Tool name 'list_refs' and description 'List all references with optional prefix filter' indicate a retrieval operation without side effects. No creation, modification, deletion, or execution is described.
Attacks that exploit this kind of access
List all references with optional prefix filter. It is categorised as a Read tool in the Substrate MCP Server, which means it retrieves data without modifying state.
Register the Substrate MCP server in PolicyLayer and add a rule for list_refs: 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.
list_refs 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 list_refs 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 list_refs. 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.
list_refs 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 →