MCP server

Jeff-Gemma4-E2B support triage

hf/Aratan/jeff-gemma4-triage

Checked 26 Oct 2026, 08:30 UTC · Hugging Face reports it running

Five calibrated routing decisions from one forward pass

Working at last check

Website

https://aratan-jeff-gemma4-triage.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: 26 Oct 2026, 08:30 UTC

Connect it to your agent

Add to Cursor Add to VS Code VS Code Insiders

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 jeff-gemma4-triage https://aratan-jeff-gemma4-triage.hf.space/gradio_api/mcp/

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.jeff-gemma4-triage]
url = "https://aratan-jeff-gemma4-triage.hf.space/gradio_api/mcp/"

Gemini CLI

{"mcpServers":{"jeff-gemma4-triage":{"httpUrl":"https://aratan-jeff-gemma4-triage.hf.space/gradio_api/mcp/"}}}

Cursor

{"mcpServers":{"jeff-gemma4-triage":{"url":"https://aratan-jeff-gemma4-triage.hf.space/gradio_api/mcp/"}}}

VS Code

{"servers":{"jeff-gemma4-triage":{"type":"http","url":"https://aratan-jeff-gemma4-triage.hf.space/gradio_api/mcp/"}}}

Antigravity

agy mcp add jeff-gemma4-triage https://aratan-jeff-gemma4-triage.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":"jeff-gemma4-triage","server_url":"https://aratan-jeff-gemma4-triage.hf.space/gradio_api/mcp/","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"jeff-gemma4-triage","server_url":"https://aratan-jeff-gemma4-triage.hf.space/gradio_api/mcp/"}

Related MCP servers

Jeff 1.0 Large
Calibrated decision model - state+question to probabilities
this-that-model-1.0
One forward pass, no decoding: calibrated typed decisions
this-that-model-1.2
One forward pass, no decoding: calibrated typed decisions
Model Tested
Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.
classifier.dev
Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key.
SAM3-Gemma4-CUDA
Object Multiplex
SAM3-Gemma4-CUDA
Object Multiplex
SAM3-Gemma4-CUDA
Object Multiplex

Badge for your README

[![AptLynx](https://aptlynx.net/badge/hf/Aratan/jeff-gemma4-triage.svg)](https://aptlynx.net/servers/hf/Aratan/jeff-gemma4-triage)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents