Create a named checkpoint of the entire project. Runs in background — returns immediately. If slots are full, DO NOT auto-retry — ask the user whether to delete an existing checkpoint or increase capacity.
AI agents use vigil_save 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_save creates and persists project snapshots, modifying the checkpoint store. It is reversible (checkpoints can be deleted), so it falls under Write rather than Destructive. The sibling tool vigil_delete handles irreversible removal.
From the tool's definition Creates a named checkpoint of the entire project. This is a write operation that creates new data (snapshots) reversibly—checkpoints can be deleted or overwritten per the description's mention of slot management and deletion options.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access vigil_save 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_save:
{
"version": "1",
"default": "deny",
"tools": {
"vigil_save": {
"limits": [
{
"counter": "vigil_save_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}vigil_save 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.
Create a named checkpoint of the entire project. Runs in background — returns immediately. If slots are full, DO NOT auto-retry — ask the user whether to delete an existing checkpoint or increase capacity. 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_save: 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_save 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_save 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_save. 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_save 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.