AI agents use remove_tags to create or update resources in Kontexta — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kontexta environment.
The tool removes tag associations from a file but explicitly does not delete the file itself or the global tag definitions. This is a reversible metadata modification (tags can be re-attached), making it a Write operation rather than Destructive. The blast radius is low since only a tag-to-file link is removed, with no data loss.
From the tool's definition Detach one or more tag IDs from ONE file. Destructive on the link only — does NOT delete the file or the global tag definition
Attacks that exploit this kind of access
Detach one or more tag IDs from ONE file. Destructive on the link only — does NOT delete the file or the global tag definition (orphan tags survive in. It is categorised as a Write tool in the Kontexta MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kontexta MCP server in PolicyLayer and add a rule for remove_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 Kontexta. Nothing to install.
remove_tags 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 remove_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 remove_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.
remove_tags is provided by the Kontexta MCP server (safiyu/kontexta). 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 →