NerdCabalMCP

Using NerdCabalMCP with Claude Code

Overview

This guide explains how to use the NerdCabalMCP server with Claude Code and Claude Desktop. NerdCabalMCP provides 17 specialized AI agents that assist with research, security, design, finance, operations, and enterprise IP protection.

This MCP server also includes Paper2Agent, a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.

🚀 Quick Start with Claude Code

Step 1: Install and Build the MCP Server

# Clone the repository
git clone https://github.com/Tuesdaythe13th/NerdCabalMCP.git
cd NerdCabalMCP/mcp-server

# Install dependencies
npm install

# Build the TypeScript code
npm run build

Step 2: Configure Claude Desktop

Add the following to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "nerdcabal": {
      "command": "node",
      "args": [
        "/absolute/path/to/NerdCabalMCP/mcp-server/dist/index.js"
      ],
      "env": {
        "LOG_LEVEL": "info"
      }
    }
  }
}

Important: Replace /absolute/path/to/ with the actual absolute path on your system.

Step 3: Restart Claude Desktop

Completely quit and reopen Claude Desktop for the changes to take effect.

Step 4: Verify Installation

In Claude Desktop:

  1. Start a new conversation
  2. Type @ to see available tools
  3. Look for nerdcabal tools

You should see tools like:


🤖 The 17 Specialized Agents

Enterprise IP Protection Suite (3 agents)

1. IP Analytics Engine

Tool: ip_analytics

Analyzes intellectual property patterns, portfolio valuation, and competitive scanning.

Example usage:

@nerdcabal Use ip_analytics to analyze copyright infringement patterns
for the last 90 days in portfolio PORT-001.

2. Compliance Engine

Tool: compliance_check

Validates GDPR, DMCA, EU Copyright Directive, and AI Act compliance.

Example usage:

@nerdcabal Use compliance_check to validate GDPR compliance for a system
that processes personal data with consent.

3. Archival System

Tool: archival_system

Stores IP infringement evidence with cryptographic integrity using SHA-256 chain hashing.

Example usage:

@nerdcabal Use archival_system to store evidence of copyright infringement
from https://example.com/infringement.jpg for case CASE-2026-001.

Research & Evaluation Agents (3 agents)

4. LLM Rubric Architect

Tool: llm-rubric-architect

Creates comprehensive evaluation rubrics for AI systems.

Example usage:

@nerdcabal Use llm-rubric-architect to create a rubric for evaluating
chatbot responses. Include accuracy, helpfulness, safety, and tone on a 1-5 scale.

5. Experimental Designer

Tool: experimental-designer

Designs controlled experiments with proper methodology and power analysis.

Example usage:

@nerdcabal Use experimental-designer to design an A/B test.
Hypothesis: Chain-of-thought prompting improves accuracy on math problems.
Sample size: 1000. Metric: accuracy.

6. Forensic Analyst

Tool: forensic-analyst

Detects hallucinations and errors in LLM outputs using DSMMD taxonomy.

Example usage:

@nerdcabal Use forensic-analyst to analyze this transcript for hallucinations:
[paste transcript here]

Financial & Operations Agents (2 agents)

7. Budget Agent

Tool: budget-agent

Creates budgets for grants, investor pitches, and project planning.

Example usage:

@nerdcabal Use budget-agent to create an NSF grant budget for an AI research project.
Funding target: $500,000. Timeline: 18 months.

8. Comptroller Agent

Tool: comptroller-agent

Analyzes the Iron Triangle (Speed âź· Cost âź· Quality) trade-offs.

Example usage:

@nerdcabal Use comptroller-agent to analyze trade-offs for building a new feature
in 2 weeks with $10,000 budget and production-quality requirements.

Governance & Security Agents (2 agents)

9. Administrator Agent

Tool: administrator-agent

Designs organizational structures, SOPs, and team configurations.

Example usage:

@nerdcabal Use administrator-agent to design an org chart for a distributed AI team
with 15 people across US East, US West, EU, and Asia timezones.

10. CISO Agent

Tool: ciso-agent

Performs STRIDE threat modeling and security audits.

Example usage:

@nerdcabal Use ciso-agent to perform a STRIDE threat model for an LLM API
with components: API gateway, model inference, user database.

ML Operations Agents (3 agents)

11. MLflow Agent

Tool: mlflow-agent

Generates MLflow queries for experiment tracking.

Example usage:

@nerdcabal Use mlflow-agent to create a query that finds the top 10 model runs
with highest accuracy from the last 30 days.

12. Dataset Builder

Tool: dataset-builder

Creates ML training datasets in SFT, DPO, or RLHF formats.

Example usage:

@nerdcabal Use dataset-builder to create a supervised fine-tuning dataset
for teaching Python code generation. Include 5 examples in HuggingFace format.

13. Visual Inspector

Tool: visual-inspector

Generates FiftyOne scripts for dataset visualization and quality analysis.

Example usage:

@nerdcabal Use visual-inspector to create a FiftyOne visualization script
for CIFAR-10 to find mislabeled images.

Design Agent (1 agent)

14. Creative Director

Tool: creative-director

Creates design systems, color palettes, and UI/UX specifications.

Example usage:

@nerdcabal Use creative-director to create a cyberpunk brutalist design system
with colors: black, white, red. Components: buttons, cards, navigation. Output: CSS.

Meta-Agent (1 agent)

15. Orchestrator

Tool: orchestrator

Coordinates multi-agent workflows using ADK patterns (Sequential, Parallel, Loop, Coordinator).

Example usage:

@nerdcabal Use orchestrator to create a sequential workflow:
1. experimental-designer creates an experiment
2. budget-agent creates a budget
3. administrator-agent designs the team

Paper2Agent Infrastructure (2 agents)

16-17. Paper2Agent System

The Paper2Agent system converts research papers into interactive MCP tools.

Custom Claude Agents (in .claude/agents/):


đź“– Paper2Agent Architecture

Paper2Agent is integrated into NerdCabalMCP and uses specialized agents for converting research papers to tools.

Core Components

  1. Tutorial Scanner - Identifies and categorizes tutorial materials in research codebases
  2. Tutorial Executor - Executes notebooks to generate gold-standard outputs
  3. Tool Extractor - Extracts reusable functions from tutorials
  4. Test Verifier - Creates and validates test files for extracted functions
  5. MCP Generator - Creates FastMCP servers from extracted tools

Output Structure

<project_dir>/
├── src/
│   ├── <repo_name>_mcp.py          # Generated MCP server
│   └── tools/                      # Extracted tools from tutorials
├── <repo_name>-env/                # Isolated Python environment
├── repo/<repo_name>/               # Cloned repository
├── reports/                        # Analysis reports
├── tests/                          # Generated test suites
└── notebooks/                      # Executed tutorials

MCP Server Integration

What is MCP?

Model Context Protocol (MCP) is a standardized protocol for connecting AI models with external tools and data sources. Paper2Agent generates MCP servers using FastMCP that expose research paper functionality as callable tools.

MCP Server Structure

Paper2Agent generates MCP servers with the following structure:

from fastmcp import FastMCP
from tools.example_tool import example_mcp

# Define the MCP server
mcp = FastMCP(name="ResearchPaper")

# Mount the tools
mcp.mount(example_mcp)

# Run the MCP server
if __name__ == "__main__":
    mcp.run(transport="http", host="127.0.0.1", port=8003)

Installing MCP Servers

Local MCP Server

cd <working_dir>
fastmcp install claude-code <project_dir>/src/<repo_name>_mcp.py \
  --python <project_dir>/<repo_name>-env/bin/python

Remote MCP Server (Hugging Face)

bash launch_remote_mcp.sh \
  --working_dir <working_dir> \
  --mcp_name <mcp_name> \
  --mcp_url <remote_mcp_url>

Example:

bash launch_remote_mcp.sh \
  --working_dir analysis_dir \
  --mcp_name alphagenome \
  --mcp_url https://Paper2Agent-alphagenome-mcp.hf.space

Verifying MCP Installation

# List installed MCP servers
claude mcp list

# Or inside Claude Code
\mcp

Tool Calling Format

Tool Structure

Each tool extracted by Paper2Agent follows this standardized format:

from fastmcp import FastMCP
from typing import Annotated, Literal

# Create MCP instance for the tool module
tool_mcp = FastMCP(name="tool_name")

@tool_mcp.tool
def example_tool(
    required_param: Annotated[str, "Description of required parameter"],
    optional_param: Annotated[str | None, "Description of optional parameter"] = None,
    enum_param: Annotated[Literal["option1", "option2"], "Parameter with fixed options"] = "option1",
    bool_param: Annotated[bool, "Boolean flag description"] = True,
) -> dict:
    """
    Brief description of what the tool does.
    """
    # Tool implementation

    # Return standardized format
    return {
        "message": "Description of what was done",
        "reference": "https://github.com/repo/tutorial.ipynb",
        "artifacts": [
            {
                "description": "Output file description",
                "path": "/absolute/path/to/output.csv"
            }
        ]
    }

Tool Calling Convention

All Paper2Agent tools return a standardized dictionary with:

Example Tool: Batch Variant Scoring

@score_batch_mcp.tool
def score_batch_variants(
    api_key: Annotated[str, "API key for the AlphaGenome model"],
    vcf_file: Annotated[str | None, "Path to VCF/TSV/CSV file with columns: variant_id, CHROM, POS, REF, ALT"] = None,
    organism: Annotated[Literal["human", "mouse"], "Organism to score against"] = "human",
    sequence_length: Annotated[Literal["2KB", "16KB", "100KB", "500KB", "1MB"], "Context window"] = "1MB",
    score_rna_seq: Annotated[bool, "Include RNA-seq signal prediction"] = True,
    score_atac: Annotated[bool, "Include ATAC"] = True,
    out_prefix: Annotated[str | None, "Output file prefix"] = None,
) -> dict:
    """
    Score genetic variants in batch across multiple regulatory modalities using AlphaGenome.
    """
    # Implementation details...

    return {
        "message": f"Scored {len(vcf)} variants and saved results table",
        "reference": "https://github.com/AlphaPOP/blob/main/score_batch.ipynb",
        "artifacts": [
            {
                "description": "Variant scores results table",
                "path": str(download_path.resolve())
            }
        ]
    }

Calling Tools in Claude Code

When the MCP server is connected to Claude Code, tools are automatically discovered and can be called:

User: Analyze heart gene expression data with AlphaGenome MCP to identify the
causal gene for the variant chr11:116837649:T>G, associated with
Hypoalphalipoproteinemia.

Claude Code will:

  1. Detect available MCP tools
  2. Select the appropriate tool (e.g., score_batch_variants)
  3. Format the input data correctly
  4. Call the tool with proper parameters
  5. Process and present the results

Running Paper2Agent

Basic Usage

cd Paper2Agent

bash Paper2Agent.sh \
  --project_dir <PROJECT_DIR> \
  --github_url <GITHUB_URL>

Advanced Usage

# Process specific tutorials only
bash Paper2Agent.sh \
  --project_dir <PROJECT_DIR> \
  --github_url <GITHUB_URL> \
  --tutorials <TUTORIALS_URL or TUTORIALS_TITLE>

# With API key for private repositories
bash Paper2Agent.sh \
  --project_dir <PROJECT_DIR> \
  --github_url <GITHUB_URL> \
  --api <API_KEY>

Examples

AlphaGenome Agent

bash Paper2Agent.sh \
  --project_dir AlphaGenome_Agent \
  --github_url https://github.com/google-deepmind/alphagenome \
  --api <ALPHAGENOME_API_KEY>

Scanpy Agent

bash Paper2Agent.sh \
  --project_dir Scanpy_Agent \
  --github_url https://github.com/scverse/scanpy \
  --tutorials "Preprocessing and clustering"

Available Paper MCP Servers

Pre-built MCP servers hosted on Hugging Face:

Multi-Agent System

Paper2Agent uses specialized agents for different pipeline stages:

  1. tutorial-scanner - Scans codebase for tutorial materials
  2. tutorial-executor - Executes notebooks with proper environment setup
  3. tutorial-tool-extractor-implementor - Extracts and implements tools from tutorials
  4. test-verifier-improver - Creates and validates test files
  5. environment-python-manager - Manages isolated Python environments

Each agent is invoked automatically during the Paper2Agent pipeline.

Type Annotations and Parameters

Supported Types

Paper2Agent tools use Python type hints with Annotated for documentation:

File Path Conventions

Best Practices

When Creating Tools

  1. Use clear parameter descriptions - The annotation string helps Claude understand the tool
  2. Provide sensible defaults - Optional parameters should have good default values
  3. Return standardized format - Always include message, reference, and artifacts
  4. Validate inputs - Check file existence and parameter validity
  5. Use absolute paths - Return absolute paths in artifacts for reliability

When Using Paper Agents

  1. Verify MCP connection - Use \mcp in Claude Code to confirm server is loaded
  2. Provide complete data - Include all required input files
  3. Check artifacts - Review generated output files in the artifacts list
  4. Reference original papers - Use the reference URLs to understand tool behavior
  5. Monitor execution - Check logs and reports in the reports/ directory

Code Quality and Coverage

Paper2Agent includes automated testing and quality checks:

Coverage Reports

Located in reports/coverage/:

Quality Reports

Located in reports/quality/pylint/:

Combined Report

reports/coverage_and_quality_report.md provides comprehensive metrics for all generated tools.

Prerequisites

Installation

# Clone repository
git clone https://github.com/jmiao24/Paper2Agent.git
cd Paper2Agent

# Install dependencies
pip install fastmcp

# Install and configure Claude Code
npm install -g @anthropic-ai/claude-code
claude

Citation

@misc{miao2025paper2agent,
  title={Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents},
  author={Jiacheng Miao and Joe R. Davis and Jonathan K. Pritchard and James Zou},
  year={2025},
  eprint={2509.06917},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2509.06917},
}

đź’ˇ How to Use Agents in Claude Code

Basic Usage Pattern

Every agent follows this simple pattern:

@nerdcabal Use [agent-name] to [describe task]

Multi-Agent Workflows

You can chain multiple agents together:

@nerdcabal Let's plan a complete research project:

1. Use experimental-designer to design an A/B test for prompt engineering
2. Use budget-agent to create a 6-month budget for $200k
3. Use administrator-agent to design a team of 5 people
4. Use ciso-agent to identify security risks

Claude will execute each agent sequentially, passing context between them.

Checking Available Tools

In Claude Code or Claude Desktop:

Type @ to see all available tools
Look for tools starting with the nerdcabal prefix

Or use the MCP command:

\mcp

đź§Ş Testing Your Setup

See the comprehensive TESTING.md guide for:

Quick Verification Test

Try this in Claude Desktop:

@nerdcabal Use llm-rubric-architect to create a simple rubric for
evaluating AI assistants on helpfulness and accuracy. Use a 1-3 scale.

If you get a well-formatted rubric back, your MCP is working perfectly!


đź”§ Troubleshooting

“Tools not appearing in Claude Desktop”

  1. Check configuration file path:
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
    • Linux: ~/.config/Claude/claude_desktop_config.json
  2. Verify absolute path:
    "args": ["/Users/yourname/NerdCabalMCP/mcp-server/dist/index.js"]
    

    NOT:

    "args": ["~/NerdCabalMCP/mcp-server/dist/index.js"]  // ❌ Won't work
    
  3. Completely restart Claude Desktop:
    • Quit the application entirely (not just close window)
    • Reopen Claude Desktop
  4. Check logs:
    # macOS
    tail -f ~/Library/Logs/Claude/mcp*.log
    
    # Linux
    tail -f ~/.config/Claude/logs/mcp*.log
    

“Server not starting”

  1. Rebuild the server:
    cd mcp-server
    npm run build
    
  2. Test standalone:
    node dist/index.js
    

    Should output: MCP server running on stdio

  3. Check Node.js version:
    node --version  # Should be v18.0.0 or higher
    

“Agent returns error”

  1. Verify you’re using correct agent name (see list above)
  2. Check input format matches the agent’s schema
  3. Enable debug logging in config:
    "env": {
      "LOG_LEVEL": "debug"
    }
    

📚 Additional Resources

NerdCabalMCP Documentation

External Resources


🎯 Next Steps

  1. Test individual agents: Use TESTING.md to verify each agent works
  2. Try multi-agent workflows: Combine agents for complex tasks
  3. Explore Paper2Agent: Convert research papers to MCP tools
  4. Read the docs: Check docs/ for detailed guides
  5. Join discussions: https://github.com/Tuesdaythe13th/NerdCabalMCP/discussions

Built with ❤️ by TUESDAY and the OG NerdCabal

WE RESPECT THE RULES OF THE SEA.