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

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

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. 16 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.

# List all 16 available MCP servers
uvx iowarp-agent-toolkit mcp-servers

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

# AI prompts also available
uvx iowarp-agent-toolkit prompts                    # List all prompts
uvx iowarp-agent-toolkit prompt code-coverage-prompt # Use a prompt

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

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

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

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

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

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

"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

"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

"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

"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

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

Tools used: line_plot, data_info

# Verify server name is correct
uvx iowarp-agent-toolkit mcp-servers

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

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

# 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

• 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

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

we welcome more sponsorships. please contact the Principal Investigator

• 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

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