Allows AI agents to interact with a Neovim instance, providing tools for opening files, executing Lua, fetching diagnostics, setting the quickfix list, and showing notifications.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@nvim-editor-mcp Show diagnostics for the current buffer"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server bridging tool calls to Neovim editor actions via RPC.
Exposes Neovim operations (open files, run Lua, diagnostics, quickfix, notifications) as Model Context Protocol tools, so AI agents can drive your editor.
Requires uv and Python ≥ 3.11.
uv tool install .This puts nvim-editor-mcp on your PATH.
Related MCP server: @aetherall/mcp-nvim-tmux
nvim-editor-mcp auto-discovers the socket from the $NVIM env var, which is
set when the mcp is started from nvim, e.g. through
codecompanion
nvim-editor-mcp
# Explicit socket path
nvim-editor-mcp --socket /tmp/nvim.sockThe server starts in stdio MCP mode. If no socket is given and $NVIM is
unset, it starts anyway and discovers the socket on the first tool call (via
attach_nvim).
Tool | Description |
| Connect to a Neovim instance by socket path |
| Detach from the current Neovim instance |
| Open a file at a specific line |
| Populate the quickfix list |
| Fetch LSP diagnostics |
| Execute arbitrary Lua in Neovim |
| Show a notification in Neovim |
{
"mcpServers": {
"nvim-editor-mcp": {
"command": "nvim-editor-mcp"
}
}
}uv syncThis creates a .venv and installs all runtime + dev dependencies.
uv run ruff check .
uv run ruff format .uv run ty checkuv run pytestuv run ruff check . && uv run ruff format --check . && uv run ty check && uv run pytestGPL-2.0
This server cannot be deployed
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
