Restore project to a checkpoint state. Quicksaves current state first. Displaced files (modified + new) are preserved in .claude/vigil/artifacts/ — nothing is ever deleted. For individual file/function restores, use vigil_diff to get the content and apply with Edit.
AI agents use vigil_restore to create or update resources in Claude Vigil — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Vigil environment.
vigil_restore performs selective file restoration, which modifies project state by overwriting current file contents with checkpoint versions. This is a Write operation because: (1) it changes file state reversibly, (2) a safeguard exists (displaced files are preserved in artifacts), and (3) users can recover from the operation via diffs and re-editing.
From the tool's definition Tool description states: 'Restore project to a checkpoint state' and 'Displaced files (modified + new) are preserved' — this modifies project files by reverting them to a previous state.
Documented attack patterns abuse exactly the kind of access vigil_restore 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_restore:
{
"version": "1",
"default": "deny",
"tools": {
"vigil_restore": {
"limits": [
{
"counter": "vigil_restore_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}vigil_restore stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Restore project to a checkpoint state. Quicksaves current state first. Displaced files (modified + new) are preserved in .claude/vigil/artifacts/ — nothing is ever deleted. For individual file/function restores, use vigil_diff to get the content and apply with Edit. It is categorised as a Write tool in the Claude Vigil MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Vigil MCP server in PolicyLayer and add a rule for vigil_restore: 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_restore 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 vigil_restore 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_restore. 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_restore 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.