iowarp-agent-toolkit 1.0.3

Agent Toolkit - MCP Servers, Clients, and Tools for AI Agents

Agent Toolkit

Agent Toolkit - Part of the IoWarp platform's tooling layer for AI agents. A comprehensive collection of tools, skills, plugins, and extensions. Currently featuring 15+ Model Context Protocol (MCP) servers for scientific computing, with plans to expand to additional agent capabilities. Enables AI agents to interact with HPC resources, scientific data formats, and research datasets.

Website | IOWarp

Chat with us on Zulip or join us

Developed by Gnosis Research Center

---

❌ Without Agent Toolkit

Working with scientific data and HPC resources requires manual scripting and tool-specific knowledge:

• ❌ Write custom scripts for every HDF5/Parquet file exploration
• ❌ Manually craft Slurm job submission scripts
• ❌ Switch between multiple tools for data analysis
• ❌ No AI assistance for scientific workflows
• ❌ Repetitive coding for common research tasks

✅ With Agent Toolkit

AI agents handle scientific computing tasks through natural language:

• ✅ "Analyze the temperature dataset in this HDF5 file" - HDF5 MCP does it
• ✅ "Submit this simulation to Slurm with 32 cores" - Slurm MCP handles it
• ✅ "Find papers on neural networks from ArXiv" - ArXiv MCP searches
• ✅ "Plot the results from this CSV file" - Plot MCP visualizes
• ✅ "Optimize memory usage for this pandas DataFrame" - Pandas MCP optimizes

One unified interface. 15 MCP servers. 150+ specialized tools. Built for research.

Agent Toolkit is part of the IoWarp platform's comprehensive tooling ecosystem for AI agents. It brings AI assistance to your scientific computing workflow—whether you're analyzing terabytes of HDF5 data, managing Slurm jobs across clusters, or exploring research papers. Built by researchers, for researchers, at Illinois Institute of Technology with NSF support.

Part of IoWarp Platform: Agent Toolkit is the tooling layer of the IoWarp platform, providing skills, plugins, and extensions for AI agents working in scientific computing environments.

One simple command. Production-ready, fully typed, MIT licensed, and beta-tested in real HPC environments.

🚀 Quick Installation

One Command for Any Server

# List all 15 available MCP servers
uvx agent-toolkit

# Run any server instantly
uvx agent-toolkit hdf5
uvx agent-toolkit pandas
uvx agent-toolkit slurm

Install in Cursor

Add to your Cursor ~/.cursor/mcp.json:

{
  "mcpServers": {
    "hdf5-mcp": {
      "command": "uvx",
      "args": ["agent-toolkit", "hdf5"]
    },
    "pandas-mcp": {
      "command": "uvx",
      "args": ["agent-toolkit", "pandas"]
    },
    "slurm-mcp": {
      "command": "uvx",
      "args": ["agent-toolkit", "slurm"]
    }
  }
}

See Cursor MCP docs for more info.

Install in Claude Code

# Add HDF5 MCP
claude mcp add hdf5-mcp -- uvx agent-toolkit hdf5

# Add Pandas MCP
claude mcp add pandas-mcp -- uvx agent-toolkit pandas

# Add Slurm MCP
claude mcp add slurm-mcp -- uvx agent-toolkit slurm

See Claude Code MCP docs for more info.

Install in VS Code

Add to your VS Code MCP config:

"mcp": {
  "servers": {
    "hdf5-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": ["agent-toolkit", "hdf5"]
    },
    "pandas-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": ["agent-toolkit", "pandas"]
    }
  }
}

See VS Code MCP docs for more info.

Install in Claude Desktop

Edit claude_desktop_config.json:

{
  "mcpServers": {
    "hdf5-mcp": {
      "command": "uvx",
      "args": ["agent-toolkit", "hdf5"]
    },
    "arxiv-mcp": {
      "command": "uvx",
      "args": ["agent-toolkit", "arxiv"]
    }
  }
}

See Claude Desktop MCP docs for more info.

Available Packages

📦 Package	📌 Ver	🔧 System	📋 Description	⚡ Install Command
adios	1.0	Data I/O	Read data using ADIOS2 engine	uvx agent-toolkit adios
arxiv	1.0	Research	Fetch research papers from ArXiv	uvx agent-toolkit arxiv
chronolog	1.0	Logging	Log and retrieve data from ChronoLog	uvx agent-toolkit chronolog
compression	1.0	Utilities	File compression with gzip	uvx agent-toolkit compression
darshan	1.0	Performance	I/O performance trace analysis	uvx agent-toolkit darshan
hdf5	2.1	Data I/O	HPC-optimized scientific data with 27 tools, AI insights, caching, streaming	uvx agent-toolkit hdf5
jarvis	1.0	Workflow	Data pipeline lifecycle management	uvx agent-toolkit jarvis
lmod	1.0	Environment	Environment module management	uvx agent-toolkit lmod
ndp	1.0	Data Protocol	Search and discover datasets across CKAN instances	uvx agent-toolkit ndp
node-hardware	1.0	System	System hardware information	uvx agent-toolkit node-hardware
pandas	1.0	Data Analysis	CSV data loading and filtering	uvx agent-toolkit pandas
parallel-sort	1.0	Computing	Large file sorting simulation	uvx agent-toolkit parallel-sort
parquet	1.0	Data I/O	Read Parquet file columns	uvx agent-toolkit parquet
plot	1.0	Visualization	Generate plots from CSV data	uvx agent-toolkit plot
slurm	1.0	HPC	Job submission simulation	uvx agent-toolkit slurm

---

📖 Usage Examples

HDF5: Scientific Data Analysis

"What datasets are in climate_simulation.h5? Show me the temperature field structure and read the first 100 timesteps."

Tools used: open_file, analyze_dataset_structure, read_partial_dataset, list_attributes

Slurm: HPC Job Management

"Submit simulation.py to Slurm with 32 cores, 64GB memory, 24-hour runtime. Monitor progress and retrieve output when complete."

Tools used: submit_slurm_job, check_job_status, get_job_output

ArXiv: Research Discovery

"Find the latest papers on diffusion models from ArXiv, get details on the top 3, and export citations to BibTeX."

Tools used: search_arxiv, get_paper_details, export_to_bibtex, download_paper_pdf

Pandas: Data Processing

"Load sales_data.csv, clean missing values, compute statistics by region, and save as Parquet with compression."

Tools used: load_data, handle_missing_data, groupby_operations, save_data

Plot: Data Visualization

"Create a line plot showing temperature trends over time from weather.csv with proper axis labels."

Tools used: line_plot, data_info

---

🚨 Troubleshooting

Server Not Found Error

If uvx agent-toolkit <server-name> fails:

# Verify server name is correct
uvx agent-toolkit

# Common names: hdf5, pandas, slurm, arxiv (not hdf5-mcp, pandas-mcp)

Import Errors or Missing Dependencies

For development or local testing:

cd agent-toolkit-mcp-servers/hdf5
uv sync --all-extras --dev
uv run hdf5-mcp

uvx Command Not Found

Install uv package manager:

# Linux/macOS
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

# Or via pip
pip install uv

---

Team

• Gnosis Research Center (GRC) - Illinois Institute of Technology | Lead
• HDF Group - Data format and library developers | Industry Partner
• University of Utah - Research collaboration | Domain Science Partner

Sponsored By

NSF (National Science Foundation) - Supporting scientific computing research and AI integration initiatives

we welcome more sponsorships. please contact the Principal Investigator

Ways to Contribute

• Submit Issues: Report bugs or request features via GitHub Issues
• Develop New MCPs: Add servers for your research tools (CONTRIBUTING.md)
• Improve Documentation: Help make guides clearer
• Share Use Cases: Tell us how you're using Agent Toolkit in your research

Full Guide: CONTRIBUTING.md

Community & Support

• Chat: Zulip Community
• Join: Invitation Link
• Issues: GitHub Issues
• Discussions: GitHub Discussions
• Website: https://iowarp.ai/agent-toolkit/
• Project: IOWarp Project

---