// MCP TOOL REFERENCE

vigil_delete

ServerClaude Vigil
CategoryDestructive

WHAT IT DOES

What vigil_delete does on Claude Vigil

AI agents call vigil_delete to permanently remove resources in Claude Vigil — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

THE RISK

Critical Risk

Why vigil_delete needs a policy

This tool irreversibly deletes checkpoints (snapshots of project state). While the description notes that artifact directories are not deleted, the core function removes recovery points that cannot be undone. Deletion of backups/snapshots is a destructive action that eliminates the ability to restore previous project states. The ability to delete all checkpoints in one operation increases the blast radius.

From the tool's definition Tool name is 'vigil_delete' and description states 'Delete a checkpoint and reclaim disk space' with ability to 'delete all checkpoints' via all=true parameter.

Documented attack patterns abuse exactly the kind of access vigil_delete gives an agent:

POLICY

How to control vigil_delete

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_delete:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "vigil_delete"
  ]
}

vigil_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Claude Vigil — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Claude Vigil tools

Write vigil_restore Restore project to a checkpoint state. Quicksaves current state first. Displaced files (mo Write vigil_save Create a named checkpoint of the entire project. Runs in background — returns immediately. Read vigil_diff Search and investigate previous versions of your codebase. Compare checkpoint vs current w Read vigil_list List all checkpoints and disk usage. With name: list files inside that checkpoint.

All 5 Claude Vigil tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Claude Vigil → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about vigil_delete

What does the vigil_delete tool do? +

Delete a checkpoint and reclaim disk space. Use all=true to delete all checkpoints. Note: artifact directories from previous restores are NOT deleted — ask the user if they want you to clean those up separately. It is categorised as a Destructive tool in the Claude Vigil MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on vigil_delete? +

Register the Claude Vigil MCP server in PolicyLayer and add a rule for vigil_delete: 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.

What risk level is vigil_delete? +

vigil_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit vigil_delete? +

Yes. Add a rate_limit block to the vigil_delete 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.

How do I block vigil_delete completely? +

Set action: deny in the PolicyLayer policy for vigil_delete. 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.

What MCP server provides vigil_delete? +

vigil_delete 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.

Enforce policy on every Claude Vigil tool call.

Start from Claude Vigil, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

5 Claude Vigil tools catalogued and risk-classified — across an index of 43,000+ MCP servers.