Get all tags from a note (both inline and frontmatter).
AI agents call obsidian_get_tags to retrieve information from Mcp Apple Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing tag metadata from a note without creating, modifying, or deleting any data. It is a pure read operation that poses minimal risk if misused by an AI agent, as it cannot alter vault state or trigger unintended consequences.
From the tool's definition Tool name is 'obsidian_get_tags' and description states 'Get all tags from a note' — a retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
Get all tags from a note (both inline and frontmatter). It is categorised as a Read tool in the Mcp Apple Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Mcp Apple Obsidian MCP server in PolicyLayer and add a rule for obsidian_get_tags: 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_get_tags is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the obsidian_get_tags 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_get_tags. 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_get_tags 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 →