Skip to main content

Open Source MCP Servers for Scientific Computing

Project description

IoWarp MCPs

License: MIT PyPI version Python CI Coverage

Tests WRP Framework

Ruff MyPy uv pip-audit

Collection of MCP servers specifically designed for scientific computing research that enable AI agents and LLMs to interact with data analysis tools, HPC resources, and research datasets through a standardized protocol.

More info at: https://iowarp.github.io/iowarp-mcps/

Quick Installation

All our packages are released on PyPI for easy installation and usage.

Simple Command

# Run any MCP server directly
uvx iowarp-mcps <server-name>

List All MCPs

# See all available MCP servers
uvx iowarp-mcps

Get Started with a Simple Command

# Example: Run the pandas MCP server
uvx iowarp-mcps pandas

# Example: Run the plot MCP server  
uvx iowarp-mcps plot

# Example: Run the slurm MCP server
uvx iowarp-mcps slurm

Available Packages

📦 Package 🔧 System 📋 Description Install Command
adios Data I/O Read data using ADIOS2 engine uvx iowarp-mcps adios
arxiv Research Fetch research papers from ArXiv uvx iowarp-mcps arxiv
chronolog Logging Log and retrieve data from ChronoLog uvx iowarp-mcps chronolog
compression Utilities File compression with gzip uvx iowarp-mcps compression
darshan Performance I/O performance trace analysis uvx iowarp-mcps darshan
hdf5 Data I/O List HDF5 files from directories uvx iowarp-mcps hdf5
jarvis Workflow Data pipeline lifecycle management uvx iowarp-mcps jarvis
lmod Environment Environment module management uvx iowarp-mcps lmod
node-hardware System System hardware information uvx iowarp-mcps node-hardware
pandas Data Analysis CSV data loading and filtering uvx iowarp-mcps pandas
parallel-sort Computing Large file sorting simulation uvx iowarp-mcps parallel-sort
parquet Data I/O Read Parquet file columns uvx iowarp-mcps parquet
plot Visualization Generate plots from CSV data uvx iowarp-mcps plot
slurm HPC Job submission simulation uvx iowarp-mcps slurm

Members

Primary Institution:

Collaborating Institutions:

  • 📊 HDF Group - Data format and library developers

Sponsors

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

Development & Publishing

Testing Development Versions

Development versions are automatically published to TestPyPI on every commit to main:

# Install latest dev version from TestPyPI
uvx --index-url https://test.pypi.org/simple/ iowarp-mcps

Creating Releases

git tag v1.2.3
git push origin v1.2.3

Contributing

We welcome contributions in any form!

Ways to Contribute:

  • Submit Issues: Report any problems or bugs you encounter
  • Request Features: Submit an issue requesting a new MCP server or functionality
  • Develop: Try your hand at developing new MCP servers

Find our comprehensive contribution/development/debugging guide here.

Get Help & Connect

Reach out to us on Zulip: IoWarp-mcp Community Chat


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

iowarp_mcps-0.3.11.tar.gz (9.4 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

iowarp_mcps-0.3.11-py3-none-any.whl (9.5 MB view details)

Uploaded Python 3

File details

Details for the file iowarp_mcps-0.3.11.tar.gz.

File metadata

  • Download URL: iowarp_mcps-0.3.11.tar.gz
  • Upload date:
  • Size: 9.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for iowarp_mcps-0.3.11.tar.gz
Algorithm Hash digest
SHA256 26292e1259596910085e3d6967b10cbccd830b4b4aef890977dd26bcc2d31b1b
MD5 cf22205133afcf73de33b89dfc2d2b2f
BLAKE2b-256 400ed32fda45210c2f13945c436d51d9a496941f4258808e173af696923e7c5d

See more details on using hashes here.

Provenance

The following attestation bundles were made for iowarp_mcps-0.3.11.tar.gz:

Publisher: publish.yml on iowarp/iowarp-mcps

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file iowarp_mcps-0.3.11-py3-none-any.whl.

File metadata

  • Download URL: iowarp_mcps-0.3.11-py3-none-any.whl
  • Upload date:
  • Size: 9.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for iowarp_mcps-0.3.11-py3-none-any.whl
Algorithm Hash digest
SHA256 7a0b3967f769c2643a5ee84119b564718567664c32b246031e5e93531257e9e7
MD5 e2457c478a05f842ea2166f5c79fafec
BLAKE2b-256 45e332fccf3b02505fd3214df4f4cfa16bd36c22a5ff80a05c7eb4425192e335

See more details on using hashes here.

Provenance

The following attestation bundles were made for iowarp_mcps-0.3.11-py3-none-any.whl:

Publisher: publish.yml on iowarp/iowarp-mcps

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page