AI agents use obsidian_remove_topic 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.
This tool removes a configuration/mapping entry (topic to folder association) but explicitly does not delete or modify any actual notes or files. It is a reversible write operation on metadata/configuration, not a destructive action on content. The blast radius is low since no files are affected.
From the tool's definition Forgets a topic → folder mapping. Existing notes in the folder are not touched.
Attacks that exploit this kind of access
Forgets a topic → folder mapping. Existing notes in the folder are not touched. 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_remove_topic: 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_remove_topic 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_remove_topic 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_remove_topic. 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_remove_topic 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 →