mcp-neovim-server
by
Control Neovim using Model Context Protocol (MCP) and the official neovim/node-client JavaScript library
What is mcp-neovim-server
Neovim MCP Server
A proof of concept integration between Claude Desktop (or any client) and Neovim using Model Context Protocol (MCP) and the official neovim/node-client JavaScript library. This server leverages Vim's native text editing commands and workflows, which Claude already understands, to create a lightweight code or general purpose AI text assistance layer.
Features
- Connects to your nvim instance if you expose a socket file, for example
--listen /tmp/nvim
, when starting nvim - Views your current buffers
- Gets cursor location, mode, file name
- Runs vim commands and optionally shell commands through vim
- Can make edits using insert or replacement
API
Resources
nvim://session
: Current neovim text editor sessionnvim://buffers
: List of all open buffers in the current Neovim session with metadata including modified status, syntax, and window IDs
Tools
- vim_buffer
- Current VIM text editor buffer with line numbers shown
- Input
filename
(string) - Filename is ignored, returns a string of numbered lines with the current active buffer content
- vim_command
- Send a command to VIM for navigation, spot editing, and line deletion
- Input
command
(string) - Runs a vim command first passed through
nvim.replaceTermcodes
. Multiple commands will work if separated by newlines - On error,
'nvim:errmsg'
contents are returned
- vim_status
- Get the status of the VIM editor
- Status contains cursor position, mode, filename, visual selection, window layout, current tab, marks, registers, and working directory
- vim_edit
- Edit lines using insert, replace, or replaceAll in the VIM editor
- Input
startLine
(number),mode
("insert"
|"replace"
|"replaceAll"
),lines
(string) - insert will insert lines at startLine
- replace will replace lines starting at startLine
- replaceAll will replace the entire buffer contents
- vim_window
- Manipulate Neovim windows (split, vsplit, close, navigate)
- Input
command
(string: "split", "vsplit", "only", "close", "wincmd h/j/k/l") - Allows window management operations
- vim_mark
- Set a mark at a specific position
- Input
mark
(string: a-z),line
(number),column
(number) - Sets named marks at specified positions
- vim_register
- Set content of a register
- Input
register
(string: a-z or "),content
(string) - Manages register contents
- vim_visual
- Make a visual selection
- Input
startLine
(number),startColumn
(number),endLine
(number),endColumn
(number) - Creates visual mode selections
Using this simple set of tools, Claude can peer into your neovim session to answer questions as well as make edits to the buffer.
Limitations
- This is a quick proof of concept to experiment with Model Context Protocol. Use at your own risk.
- May not interact well with a custom neovim config!
- Error handling could be better.
- Sometimes Claude doesn't get the vim command input just right.
Configuration
Environment Variables
ALLOW_SHELL_COMMANDS
: Set to 'true' to enable shell command execution (e.g.!ls
). Defaults to false for security.NVIM_SOCKET_PATH
: Set to the path of your Neovim socket. Defaults to '/tmp/nvim' if not specified.
Usage with Claude Desktop
Add this to your claude_desktop_config.json
:
{
"mcpServers": {
"MCP Neovim Server": {
"command": "npx",
"args": [
"-y",
"mcp-neovim-server"
],
"env": {
"ALLOW_SHELL_COMMANDS": "true",
"NVIM_SOCKET_PATH": "/tmp/nvim"
}
}
}
}
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Leave a Comment
Comments section will be available soon. Stay tuned!
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
Ableton Live MCP Server
MCP Server implementation for Ableton Live OSC control
Airbnb MCP Server
AI Agent Marketplace Index Search MCP Server
MCP Server for AI Agent Marketplace Index from DeepNLP
Algorand MCP Implementation
Algorand Model Context Protocol (Server & Client)
mcp-server-apache-airflow
pypi.org/project/mcp-server-apache-airflow/
airtable-mcp-server
๐๏ธ๐ค Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases
Airtable MCP Server
Search, create and update Airtable bases, tables, fields, and records using Claude Desktop and MCP (Model Context Protocol) clients
Alphavantage MCP Server
A MCP server for the stock market data API, Alphavantage API.
Amadeus MCP Server
Amadeus MCP(Model Context Protocol) Server
Anki MCP Server
An MCP server for Anki
Submit Your MCP Server
Share your MCP server with the community
Submit Now