zk_get_all_tags
AI agents call zk_get_all_tags to retrieve information from Zettelkasten without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries tags from the Zettelkasten system with no apparent side effects. It follows the read operation pattern seen in sibling tools like zk_get_note, zk_list_notes_by_date, and zk_find_* operations. The lack of description lowers confidence slightly, but the name unambiguously indicates a retrieval operation.
From the tool's definition Tool name 'zk_get_all_tags' clearly indicates retrieval of tag data. No description provided, but the naming convention and sibling context (list, get, find operations) strongly suggest a read-only query operation.
Attacks that exploit this kind of access
zk_get_all_tags. It is categorised as a Read tool in the Zettelkasten MCP Server, which means it retrieves data without modifying state.
Register the Zettelkasten MCP server in PolicyLayer and add a rule for zk_get_all_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 Zettelkasten. Nothing to install.
zk_get_all_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 zk_get_all_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 zk_get_all_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.
zk_get_all_tags is provided by the Zettelkasten MCP server (entanglr/zettelkasten-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 →