List all checkpoints and disk usage. With name: list files inside that checkpoint.
AI agents call vigil_list to retrieve information from Claude Vigil without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing checkpoint metadata and file inventory without creating, modifying, deleting, or executing any operations. It has no side effects and poses minimal risk if invoked by an AI agent—at worst, it returns information about existing checkpoints. The low severity reflects that read-only access to checkpoint metadata is a standard, safe operation within a version-control-like system.
From the tool's definition The tool description states it 'List[s] all checkpoints and disk usage. With name: list files inside that checkpoint.' The verbs 'list' and 'show usage information' are purely informational queries with no modification or deletion of data.
Documented attack patterns abuse exactly the kind of access vigil_list gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Vigil, and nothing reaches the server without passing your rules. This is the rule we recommend for vigil_list:
{
"version": "1",
"default": "deny",
"tools": {
"vigil_list": {}
}
}vigil_list is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List all checkpoints and disk usage. With name: list files inside that checkpoint. It is categorised as a Read tool in the Claude Vigil MCP Server, which means it retrieves data without modifying state.
Register the Claude Vigil MCP server in PolicyLayer and add a rule for vigil_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 Claude Vigil. Nothing to install.
vigil_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 vigil_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 vigil_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.
vigil_list is provided by the Claude Vigil MCP server (vvkmnn/claude-vigil-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Vigil, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Claude Vigil tools catalogued and risk-classified — across an index of 43,000+ MCP servers.