Create a new note
AI agents use vault_create to create or update resources in Connect MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Connect MCP environment.
Creating a note is a write operation that adds data to the system. It is reversible (notes can be deleted) and does not execute code, destroy data irreversibly, or move money. Severity is medium because an agent could create numerous notes to fill storage or clutter the vault, but the effect is not catastrophic and can be undone. Confidence is high because the description is explicit and unambiguous.
From the tool's definition Tool name is 'vault_create' and description states 'Create a new note' — this is a reversible write operation that creates new data in the vault.
Attacks that exploit this kind of access
Create a new note. It is categorised as a Write tool in the Connect MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Connect MCP server in PolicyLayer and add a rule for vault_create: 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 Connect MCP. Nothing to install.
vault_create 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 vault_create 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_create. 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_create is provided by the Connect MCP server (joch/obsidian-connect-mcp). 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 →