AI agents use add_virtual_text 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.
The tool adds virtual text to a Neovim buffer, which is a reversible state modification (Write category). While the description is empty, the name and server context indicate this modifies editor content. Severity is high because an AI agent could inject misleading or malicious virtual text to deceive users about code content, though it's reversible.
From the tool's definition Tool name 'add_virtual_text' and server description indicates ability to 'control running Neovim sessions' with 'command execution' capabilities. Virtual text modification is a write operation that alters editor state.
Documented attack patterns abuse exactly the kind of access add_virtual_text 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_text:
{
"version": "1",
"default": "deny",
"tools": {
"add_virtual_text": {
"limits": [
{
"counter": "add_virtual_text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_virtual_text 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_text. 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_text: 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_text 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_text 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_text. 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_text 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.