3D Visualizer MCP Server

View, compare and inspect point clouds, meshes, gaussian splats, depth maps and disparity images in your editor or browser - with Rust and WebAssembly doing the heavy decoding, so files with millions of points open in seconds. It runs locally over stdio via the published package.

People who work with 3d visualization, colmap and depth estimation and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-09-10 · ★ 18 · #49 OF 106 MAINTAINED AI & ML · VERIFIED 2026-09-18

MIT · TypeScript servers · how we verify → /methodology

01 · Install 3D Visualizer

Claude Code

claude mcp add kleinicke-ply-visualizer -- uvx 3d-visualizer

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "kleinicke-ply-visualizer": {
      "command": "uvx",
      "args": [
        "3d-visualizer"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package 3d-visualizer - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.kleinicke is GitHub-verified and matches the repo owner

03 · What 3D Visualizer can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

python-v0.4.2 · 2026-09-08

3D Visualizer is now available on PyPI as 3d-visualizer. The Python import remains ply_visualizer; existing ply-viewer command aliases are retained. · Install the Python library with uv add 3d-visualizer. Start MCP…

v.1.7.0 · 2026-07-19

Internal refactoring - move to svelte · Speedup for computing point clouds out of depth · Add double click onto empty region to automatically fit to point cloud · Color point clouds by any extra PLY scalar property…

v1.0.0 · 2025-08-10

04 · Who maintains 3D Visualizer

3D Visualizer is maintained by kleinicke. It's the only MCP server we track from this author; the repo dates to Jun 2025.

05 · Facts

category
AI & ML - ranked #49 of 106 actively-maintained AI & ML servers as of 2026-09-18.
release cadence
2 releases in the last 90 days (latest 2026-09-08)
registry
io.github.kleinicke/3d-visualizer (active, first published 2026-09-08 · 2 versions)
packages
pypi:3d-visualizer

06 · 3D Visualizer FAQ

What is 3D Visualizer?

View, compare and inspect point clouds, meshes, gaussian splats, depth maps and disparity images in your editor or browser - with Rust and WebAssembly doing the heavy decoding, so files with millions of points open in seconds. It runs locally over stdio via the published package.

Is 3D Visualizer still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-10 and it shipped 2 releases in the last 90 days. We re-verify nightly.

How do I install 3D Visualizer?

Run `uvx 3d-visualizer`. You can also paste the ready-made client config above.

Does 3D Visualizer run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to 3D Visualizer

More AI & ML MCP servers · Lynx · Droste · Dali by Lulu · Tools for Agents · Metrillm

More TypeScript MCP servers · Klever Vm · J-Link MCP · HOI4 Agent Tools · Wigolo · GIA - Governed Intelligence Architecture · see all