Create visual mode selections in the buffer
AI agents invoke vim_visual to trigger actions in Mcp Neovim Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Creating visual selections in a Neovim buffer is an interactive editor action that triggers state changes in the running editor process. While selecting text alone is relatively benign, visual mode selections in Neovim can be chained with subsequent commands (delete, yank, replace, etc.), and this tool interacts with an external running process. It goes beyond a simple read, qualifying as Execute.
From the tool's definition Create visual mode selections in the buffer
Attacks that exploit this kind of access
Create visual mode selections in the buffer. It is categorised as a Execute tool in the Mcp Neovim Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Neovim Server MCP server in PolicyLayer and add a rule for vim_visual: 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 Mcp Neovim Server. Nothing to install.
vim_visual is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the vim_visual 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 vim_visual. 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.
vim_visual is provided by the Mcp Neovim Server MCP server (mcp-neovim-server). 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 →