AI agents use add_virtual_texts to create or update resources in Nvim — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nvim environment.
Virtual text additions are reversible modifications to editor state (via clear_virtual_texts). This qualifies as Write rather than Read (which would be passive inspection like get_state). It's not Destructive since changes can be undone. The tool modifies a live editor session with side effects that persist until cleared or the session ends.
From the tool's definition Tool name 'add_virtual_texts' combined with sibling tools like 'clear_virtual_texts', 'highlight_range', and 'find_and_replace_buf' on a Neovim control server indicates modification of editor state.
Documented attack patterns abuse exactly the kind of access add_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 add_virtual_texts:
{
"version": "1",
"default": "deny",
"tools": {
"add_virtual_texts": {
"limits": [
{
"counter": "add_virtual_texts_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_virtual_texts stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
add_virtual_texts. It is categorised as a Write tool in the Nvim MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nvim MCP server in PolicyLayer and add a rule for add_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.
add_virtual_texts 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 add_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 add_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.
add_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.