Add a tag to a note.
AI agents use obsidian_add_tag to create or update resources in Mcp Apple Obsidian — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Apple Obsidian environment.
This tool creates or modifies note metadata by appending a tag, which is a reversible write operation. It does not execute code, delete data, or move money. While tags affect note organization and searchability, they can be removed without permanent data loss, making this a Write rather than Destructive operation.
From the tool's definition The tool description states 'Add a tag to a note,' which modifies note metadata. The server description confirms it provides tools for 'interacting with Obsidian vaults, notes, and application state' with 'direct file system access.' Adding a tag is a…
Attacks that exploit this kind of access
Add a tag to a note. It is categorised as a Write tool in the Mcp Apple Obsidian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Apple Obsidian MCP server in PolicyLayer and add a rule for obsidian_add_tag: 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 Apple Obsidian. Nothing to install.
obsidian_add_tag 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 obsidian_add_tag 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 obsidian_add_tag. 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.
obsidian_add_tag is provided by the Mcp Apple Obsidian MCP server (rex/mcp-apple-obsidian). 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 →