Manage vault notes. Vault scope: ${vaultScope}. Actions: list (browse notes), read (full note), create/update/delete (whole-file writes), stat (metadata), create_from_template (scaffold from template). For search strategy and conventions, read vault://overview.
AI agents call vault to permanently remove resources in Mcp Markdown Vault — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although this tool includes Read operations (list, read, stat) and Write operations (create, update, create_from_template), the presence of 'delete' capability for whole-file removal places it in the Destructive category. Deletions are irreversible and represent the most severe risk. An AI agent with unrestricted access could accidentally or maliciously delete entire notes or vault contents.
From the tool's definition Actions include: list, read, create/update/delete (whole-file writes), stat, create_from_template. The 'delete' capability irreversibly removes notes from the vault. Additionally, 'update' on whole files can overwrite existing content without recovery.
Documented attack patterns abuse exactly the kind of access vault gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Markdown Vault, and nothing reaches the server without passing your rules. This is the rule we recommend for vault:
{
"version": "1",
"default": "deny",
"hide": [
"vault"
]
}vault disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Manage vault notes. Vault scope: ${vaultScope}. Actions: list (browse notes), read (full note), create/update/delete (whole-file writes), stat (metadata), create_from_template (scaffold from template). For search strategy and conventions, read vault://overview. It is categorised as a Destructive tool in the Mcp Markdown Vault MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Markdown Vault MCP server in PolicyLayer and add a rule for vault: 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 Mcp Markdown Vault. Nothing to install.
vault 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 vault 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 vault. 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.
vault is provided by the Mcp Markdown Vault MCP server (wirux/mcp-markdown-vault). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Markdown Vault, 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 Mcp Markdown Vault tools catalogued and risk-classified — across an index of 43,000+ MCP servers.