Blatant Why
AI-powered biologics design campaign agent — multi-agent orchestration with BoltzGen, PXDesign, Protenix, and 200+ cloud tools. Antibodies, nanobodies, de novo binders, and beyond.
What is Blatant Why?
Blatant Why is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai-powered biologics design campaign agent — multi-agent orchestration with boltzgen, pxdesign, protenix, and 200+ cloud tools. antibodies, nanobodies, de novo binders, and beyond.
AI-powered biologics design campaign agent — multi-agent orchestration with BoltzGen, PXDesign, Protenix, and 200+ cloud tools. Antibodies, nanobodies, de novo binders, and beyond.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI-powered biologics design campaign agent — multi-agent orc
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx blatant-whyConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Blatant Why
Blatant Why is a multi-agent biologics design campaign engine that orchestrates AI-powered workflows for antibody, nanobody, and de novo protein binder design. It integrates BoltzGen, PXDesign, and Protenix via 11 specialized MCP servers, 21 agents, and 19 skills, connecting to cloud GPU providers (RunPod, Tamarind) and lab submission platforms (AdaptyvBio). Researchers use it to go from a target protein name to a shortlist of scored designs in roughly 20 minutes, entirely through natural language or slash commands inside Claude Code.
Prerequisites
- Node.js 18+ and Python 3.11+ installed on your machine
- uv package manager installed (https://github.com/astral-sh/uv)
- Claude Code CLI installed: npm install -g @anthropic-ai/claude-code
- At least one compute credential: RUNPOD_API_KEY (runpod.io), TAMARIND_API_KEY (tamarind.bio), or local GPU with Protenix/BoltzGen/PXDesign installed
- Optional: ADAPTYV_API_TOKEN for automated lab submission (adaptyvbio.com)
Install Claude Code CLI
Blatant Why runs inside Claude Code rather than as a standalone server. Install the CLI globally with npm.
npm install -g @anthropic-ai/claude-codeScaffold a new campaign project
Create a working directory for your biologics campaign and run the init command to scaffold the full agent/skill/MCP structure.
mkdir my-campaign && cd my-campaign
npx blatant-why initConfigure environment variables
Copy the example .env file and fill in your compute and lab credentials. At minimum, supply one cloud GPU key for remote execution or set local tool paths for on-machine GPU mode.
cp .env.example .env
# Edit .env and set at least one of:
# RUNPOD_API_KEY=...
# TAMARIND_API_KEY=...
# ADAPTYV_API_TOKEN=...
# For local GPU mode, also set:
# PROTEUS_FOLD_DIR=/path/to/protenix
# PROTEUS_PROT_DIR=/path/to/pxdesign
# PROTEUS_AB_DIR=/path/to/boltzgenLaunch Claude Code in the project directory
Start a Claude Code session inside the scaffolded campaign directory. The MCP servers and hooks are loaded automatically from the project configuration.
claudeRun a guided campaign or give a free-form prompt
Use the built-in slash command to walk through campaign planning interactively, or type a natural language design request directly. The orchestrator will invoke research, design, screening, and scoring agents sequentially.
# Guided workflow
/by:plan-campaign
# Or direct prompt
"Design VHH nanobodies against PD-L1"Review results
After the pipeline completes (typically 15-20 minutes), retrieve the ranked design shortlist with scores and optional lab-ready output files.
/by:resultsBlatant Why Examples
Client configuration
Blatant Why registers its MCP servers automatically via the init scaffold. The generated claude_desktop_config.json block looks like this:
{
"mcpServers": {
"blatant-why": {
"command": "npx",
"args": ["blatant-why"],
"env": {
"RUNPOD_API_KEY": "your_runpod_api_key",
"TAMARIND_API_KEY": "your_tamarind_api_key",
"ADAPTYV_API_TOKEN": "your_adaptyv_token"
}
}
}
}Prompts to try
Use these prompts inside Claude Code after initializing a campaign project:
- "Design VHH nanobodies targeting the RBD of SARS-CoV-2 spike protein"
- "Generate de novo binders for EGFR using PXDesign and score the top 10"
- "Run BoltzGen to produce 20 antibody candidates against PD-1 and screen for binding affinity"
- "/by:status — check the current campaign pipeline status"
- "/by:screen — trigger the screening stage on existing design candidates"Troubleshooting Blatant Why
npx blatant-why init fails with 'uv not found'
Install uv first: curl -Lf https://astral.sh/uv/install.sh | sh — then restart your terminal so the PATH is updated before running init.
Cloud GPU jobs fail or time out immediately
Verify your RUNPOD_API_KEY or TAMARIND_API_KEY is valid and that you have remaining credits. Check runpod.io or tamarind.bio dashboards. For RunPod, ensure your account has a payment method attached.
Local GPU mode cannot find Protenix or BoltzGen
Set the absolute paths in .env: PROTEUS_FOLD_DIR, PROTEUS_PROT_DIR, and PROTEUS_AB_DIR must each point to the root of the installed tool directory. Verify each path exists with ls before re-running.
Frequently Asked Questions about Blatant Why
What is Blatant Why?
Blatant Why is a Model Context Protocol (MCP) server that ai-powered biologics design campaign agent — multi-agent orchestration with boltzgen, pxdesign, protenix, and 200+ cloud tools. antibodies, nanobodies, de novo binders, and beyond. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Blatant Why?
Follow the installation instructions on the Blatant Why GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Blatant Why?
Blatant Why works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Blatant Why free to use?
Yes, Blatant Why is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Blatant Why Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Blatant Why? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Blatant Why in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Blatant Why?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.