Atlas / MCP servers / paulburgess1357 / Nvim

NvimSAFE

mcp/paulburgess1357/nvim-1

MCP server that connects AI agents to your running Neovim instance via msgpack-RPC — no plugins required.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
18 7r · 9w · 2d
Transport
stdio
License
MIT
Stars
64
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://pypi.org/project/nvim-mcp/)

[](https://glama.ai/mcp/servers/paulburgess1357/nvim-mcp)

An MCP server that gives AI agents first-class access to your running Neovim session. It connects through Neovim's native msgpack-RPC socket — no plugins required.

Works with Cursor, Claude Code, Codex, OpenCode, and any MCP-compatible client.

Before you connect an agent to Neovim, please read Working safely.

What agents can do

  • See what you see — editor mode, working directory, open buffers, window layout, cursor context, folds, selections, marks, and diagnostics.
  • Edit buffers in memory — find-and-replace or full rewrites with immediate feedback and full undo support. Nothing touches disk until you save.
  • Run any Vim command — :w, :e, :vsplit, macros, or anything else you could type at the command line.
  • Send keystrokes — navigate, enter insert mode, trigger mappings.
  • Query LSP diagnostics — errors, warnings, and hints across one buffer or the whole session.
  • Annotate code with highlights and virtual text — colored line highlights and inline/above/below text notes that never touch the buffer's real content.
  • Work with multiple instances — auto-discovers running sessions and connects to the right one. See multiple instances.

Anything you can do in Neovim, the agent can too. See the full tool reference for details.

Demos

Using nvim-mcp across two terminals

Using nvim-mcp with a terminal inside Neovim

Read from source at commit 4ec580b44f1aOBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add nvim-mcp -- uvx nvim-mcp
claude-desktop
{
  "mcpServers": {
    "nvim-mcp": {
      "command": "uvx",
      "args": [
        "nvim-mcp"
      ]
    }
  }
}
03

Exposed tools (18)

7 read · 9 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
add_virtual_textwriteAdd a virtual text annotation to a Neovim buffer. Visual only —
add_virtual_textswriteAdd multiple virtual text annotations to Neovim buffers in a
clear_highlightsdestructiveRemove all MCP highlights from a Neovim buffer. Only removes
clear_virtual_textsdestructiveRemove all MCP virtual text annotations from a Neovim buffer.
connectreadConnect to a running Neovim instance over its Unix socket or TCP address.
find_and_replace_bufwriteFind and replace text in a Neovim buffer. The edit happens in-memory
get_all_diagnosticsreadGet LSP diagnostics from all open buffers in Neovim. Read-only.
get_buf_diagnosticsreadGet LSP diagnostics for a single Neovim buffer. Read-only.
get_statereadFull snapshot of the current Neovim session. Read-only — does not
get_state_briefreadLightweight snapshot of the Neovim session for quick orientation.
highlight_rangewriteAdd a colored line highlight to a Neovim buffer. This is a visual
highlight_rangeswriteAdd colored line highlights to one or more Neovim buffers in a single
read_buf_rangereadRead a specific line range from a Neovim buffer. Read-only; reads
read_full_bufreadRead the full content of a Neovim buffer. Read-only; reads from
send_commandwriteRun one or more Vim ex commands in Neovim. This is a mutation tool —
send_keyswriteSend raw keystrokes to Neovim as if typed by the user. This is a
send_to_terminalwriteType text into a terminal buffer
write_full_bufwriteReplace the entire content of a Neovim buffer. The edit happens
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (4)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
clear_highlights, clear_virtual_texts
Why it matters. 2 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
README.md:144
The tools and agent rules are designed to use non-destructive operations — edits happen in memory, undo history is preserved, and the agent is steered toward buffer operations. But LLMs are non-determ
LOWSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:74
curl -LsSf https://astral.sh/uv/install.sh | sh
INFOInventory / provenance · inv.oversize · CWE-1104
assets/avatar.png
assets/avatar.png
Why it matters. 1295573 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 4ec580b44f1afull audit observations/trust-audit/mcp-server/paulburgess1357__nvim-1.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-074ec580b44f1aSAFEB89first audit
06

Questions

What is the Nvim MCP server?

MCP server that connects AI agents to your running Neovim instance via msgpack-RPC — no plugins required.

What tools does Nvim expose?

18 in total: 7 read-only, 9 that write, and 2 that can delete or overwrite (clear_highlights, clear_virtual_texts). Every one is listed on this page with its risk.

Is Nvim safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Nvim need?

No credential environment variables were found in its source, so it appears to need none.

How does Nvim run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as nvim-mcp.

How current is this page?

The grade is for one exact copy of the source (4ec580b44f1a), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement