AI agents use obsidian_rename_tag to create or update resources in Obsidian — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obsidian environment.
The tool modifies tag data across the entire vault, affecting potentially hundreds or thousands of notes. While reversible (a rename can be undone), the blast radius is very large—an AI agent given incorrect tag parameters could rename important organizational tags to gibberish, causing significant disruption to vault structure and discoverability.
From the tool's definition Tool description: 'Renames a tag across every note in the vault.' The verb 'renames' indicates modification of data (frontmatter, tag references) across multiple notes. This is a write operation that modifies content reversibly.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Renames a tag across every note in the vault. It is categorised as a Write tool in the Obsidian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obsidian MCP server in PolicyLayer and add a rule for obsidian_rename_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 Obsidian. Nothing to install.
obsidian_rename_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_rename_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_rename_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_rename_tag is provided by the Obsidian MCP server (yuchi-chang/obsidian-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 →