MCP server
LFM3-VL-2B-VLD multipass
hf/hugging-apps/lfm3-vl-2b-multipass
Checked 28 Oct 2026, 09:04 UTC · Hugging Face reports it running
Browser-screenshot fixed-choice decisions from a 2B VLM
Working at last check
https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Working at last check
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
- Last checked
- 28 Oct 2026, 09:04 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.
Claude Code
claude mcp add --transport http lfm3-vl-2b-multipass https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/
Claude Desktop
Settings → Connectors → Add custom connector, and paste the URL.
Codex (config.toml)
[mcp_servers.lfm3-vl-2b-multipass] url = "https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/"
Gemini CLI
{"mcpServers":{"lfm3-vl-2b-multipass":{"httpUrl":"https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/"}}}
Cursor
{"mcpServers":{"lfm3-vl-2b-multipass":{"url":"https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/"}}}
VS Code
{"servers":{"lfm3-vl-2b-multipass":{"type":"http","url":"https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/"}}}
Antigravity
agy mcp add lfm3-vl-2b-multipass https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/
ChatGPT
Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.
OpenAI API (Responses tools)
{"type":"mcp","server_label":"lfm3-vl-2b-multipass","server_url":"https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/","require_approval":"always"}
Grok (xAI API tools)
{"type":"mcp","server_label":"lfm3-vl-2b-multipass","server_url":"https://hugging-apps-lfm3-vl-2b-multipass.hf.space/gradio_api/mcp/"}
Browse
Related MCP servers
- LFM3-VL-2B-VLD
Browser-screenshot decision model (VL-D protocol) - LFM3-Audio-2B
Voice chat, ASR, translation & TTS with LFM3-Audio-2B - LFM3-VL-2B
LiquidAI vision-language model for images and video - LFM3-Omni-2B
Any-to-any: text/image/video/audio in, text or speech out - Noxgild
Secure AI access to Windows, macOS, Linux computers and a hosted Cloud Browser. - Screenrove
Real product UI captures for design reference, competitor analysis, and coding agents. - localscreenshot
Screenshot API for AI agents. Any public page as image or PDF, banners hidden, 227 countries. - Clueso
Make videos and docs with your AI agent — describe what you need, every output stays editable.
Badge for your README
[](https://aptlynx.net/servers/hf/hugging-apps/lfm3-vl-2b-multipass)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents