AI agents call clear_virtual_texts to permanently remove resources in Nvim — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing virtual texts removes previously added annotations. While this could be considered reversible (they can be re-added), the operation removes data without an undo mechanism in the protocol itself. However, given the empty description, confidence is low. The sibling tool 'add_virtual_texts' and 'clear_highlights' pattern suggests this is a cleanup/destructive operation on buffer decorations.
From the tool's definition Tool name 'clear_virtual_texts' and sibling tool 'add_virtual_texts' suggest this removes virtual text annotations from Neovim buffers. Description is empty.
Documented attack patterns abuse exactly the kind of access clear_virtual_texts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nvim, and nothing reaches the server without passing your rules. This is the rule we recommend for clear_virtual_texts:
{
"version": "1",
"default": "deny",
"hide": [
"clear_virtual_texts"
]
}clear_virtual_texts disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
clear_virtual_texts. It is categorised as a Destructive tool in the Nvim MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nvim MCP server in PolicyLayer and add a rule for clear_virtual_texts: 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 Nvim. Nothing to install.
clear_virtual_texts is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_virtual_texts 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 clear_virtual_texts. 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.
clear_virtual_texts is provided by the Nvim MCP server (paulburgess1357/nvim-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 Nvim tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 Nvim tools catalogued and risk-classified — across an index of 42,500+ MCP servers.