raft-snapshot-restore
AI agents call raft-snapshot-restore to permanently remove resources in Vault MCP Server (mschuchard) — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Restoring a Raft snapshot in Vault overwrites the entire cluster state with the snapshot data, irreversibly destroying any data written after the snapshot was taken. This is one of the most impactful operations possible on a Vault cluster, affecting all secrets, policies, and configurations. The description is empty, but the tool name alone strongly implies a destructive restore operation.
From the tool's definition Tool name 'raft-snapshot-restore' — 'restore' operation on a Raft snapshot in HashiCorp Vault
Attacks that exploit this kind of access
raft-snapshot-restore. It is categorised as a Destructive tool in the Vault MCP Server (mschuchard) MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vault MCP Server (mschuchard) MCP server in PolicyLayer and add a rule for raft-snapshot-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 Vault MCP Server (mschuchard). Nothing to install.
raft-snapshot-restore is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the raft-snapshot-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 raft-snapshot-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.
raft-snapshot-restore is provided by the Vault MCP Server (mschuchard) MCP server (mschuchard/vault-mcp-server). 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 →