skills.rest
mims-harvard
mims-harvardOFFICIAL
Explore all skills by this author →
Website𝕏@marinkazitnikGitHub

setup-chrombpnet-remote-tool

Deploy, validate, and share the ChromBPNet genomic model as a ToolUniverse remote MCP tool.

1.7k|254|Updated Mar 3, 2025
Search Tags:#genomics#Deployment#ToolUniverse#MCP Server#Deep Learning#remote tool#chrombpnet
One-click install
npx skills add https://github.com/mims-harvard/ToolUniverse --skill setup-chrombpnet-remote-tool
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: setup-chrombpnet-remote-tool
Source: https://github.com/mims-harvard/ToolUniverse/tree/main/skills/setup-chrombpnet-remote-tool
Command: npx skills add https://github.com/mims-harvard/ToolUniverse --skill setup-chrombpnet-remote-tool

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fastmcp, pyyaml, tuplatform-connect.

What problem does it solve?

Setting up the ChromBPNet deep learning model as a remotely accessible tool involves complex environment isolation, GPU configuration, credential management, and secure sharing. This Skill guides you through the entire deployment, validation, and troubleshooting workflow so the model can be invoked through a standard MCP endpoint.

Core Features & Use Cases

  • Isolated Environment Setup: Create a dedicated Python 3.12 virtual environment, install pinned requirements, and run a standard-library preflight contract check before downloading large dependencies.
  • Secure Sharing via ToolUniverse Connect: Authenticate once with browser-based device authorization (tu remote login), then share the loopback endpoint with a single tu remote share chrombpnet command without copying API keys.
  • Validation & Troubleshooting: Verify MCP tool discovery (e.g., run_chrombpnet_predict), run a verified prediction example, tune GPU workers and concurrency, and diagnose import, artifact, or authentication failures.
  • Use Case: A genomics researcher wants to expose a reviewed ChromBPNet Keras v3 model to collaborators. They follow the Skill to bind the server to loopback on port 8032, validate discovery, and relay it privately through ToolUniverse Connect.

Quick Start

Ask your AI agent to set up and validate the ChromBPNet remote tool from the ToolUniverse repository root, starting with the preflight contract check.

Frequently Asked Questions about setup-chrombpnet-remote-tool

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up ChromBPNet as a remote MCP tool?▼

Create an isolated Python 3.12 virtual environment, install ToolUniverse and the ChromBPNet requirements, set CHROMBPNET_MODEL_PATH to a reviewed Keras v3 artifact, then run the preflight check and start the server with python -m tooluniverse.remote.chrombpnet.chrombpnet_tool.

How do I share a local ChromBPNet server with collaborators?▼

Run tu remote login once to authenticate via browser device authorization, then run tu remote share chrombpnet. The command starts the loopback endpoint, validates discovery, and keeps the ToolUniverse Connect relay in the foreground.

What model format does the ChromBPNet remote tool require?▼

It requires a single administrator-reviewed Keras v3 .keras artifact referenced by CHROMBPNET_MODEL_PATH. Caller-supplied paths and legacy .h5 files are rejected, and the model provenance and license should be verified.

Why does the ChromBPNet server return 401 or 403 errors?▼

A 401/403 occurs when binding to a non-loopback address without a matching TOOLUNIVERSE_API_TOKEN bearer credential. The recommended setup binds to loopback (127.0.0.1:8032) and shares through the Connect relay instead.

Can I run the ChromBPNet remote tool without a GPU?▼

A GPU is recommended, but CPU-only execution works for small checks. Start with one worker, measure cold start and warm calls, and only increase concurrency after validating memory behavior and recoverable OOM handling.

Related Skills

Explore More Education & Research Skills→
f6ra07nk14f6ra07nk14

structcast-model

Generate PyTorch, Flax, and Keras models from YAML templates.

Community
Advanced
psd401psd401
2

meta-evolve

Evolve AI agent prompts using genetic algorithms and telemetry-driven evaluation.

Official
Advanced
MCERQUAMCERQUA
1

session-monitor-agent

Monitor chat session events across tenants to detect latency anomalies, error patterns, and attribution drift.

Community
Advanced
hungthinh04hungthinh04

jupyter-live-kernel

Maintain a persistent Python kernel for stateful code execution across JupyterLab sessions.

Community
Intermediate