Manage Neovim windows: split, close, and navigate between windows
AI agents invoke vim_window 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.
This tool controls Neovim window management — splitting, closing, and navigating windows. Closing a window could discard unsaved changes and affects the editor state externally. These are UI/session-level operations that trigger external side effects in the Neovim process, placing it in the Execute category.
From the tool's definition "Manage Neovim windows: split, close, and navigate between windows"
Attacks that exploit this kind of access
Manage Neovim windows: split, close, and navigate between windows. 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_window: 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_window 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_window 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_window. 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_window 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 →