# colabfit-mcp
An MCP server for interacting with the [ColabFit](https://materials.colabfit.org) database.
## Installation
Download source code:
```
git clone https://github.com/colabfit/colabfit-mcp.git
```
Make sure the mcp package is installed.
```
pip install mcp[cli]
```
Modify your Claude configuration file.
Navigate to Settings → Developer → Edit Config.
Your config file should look something like:
```
{
"mcpServers": {
"colabfit-mcp": {
"command": "<path to environment's mcp command>",
"args": [
"run",
"<download-location>/colabfit-mcp/colabfit_mcp.py>"
]
}
}
}
```
## Functionality
Currently, this MCP server will allow clients to query the online ColabFit database and download its dataset files.
## License
The ColabFit Tools package is copyrighted by the Regents of the University of
Minnesota. It can be freely used for educational and research purposes by
non-profit institutions and US government agencies only. Other organizations are
allowed to use the ColabFit Tools package only for evaluation purposes, and any
further uses will require prior approval. The software may not be sold or
redistributed without prior approval. One may make copies of the software for
their use provided that the copies, are not sold or distributed, are used under
the same terms and conditions. As unestablished research software, this code is
provided on an "as is'' basis without warranty of any kind, either expressed or
implied. The downloading, or executing any part of this software constitutes an
implicit agreement to these terms. These terms and conditions are subject to
change at any time without prior notice.
[mcp-name: io.github.colabfit/colabfit-mcp]: #
Raw data
{
"_id": null,
"home_page": null,
"name": "colabfit-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "machine learning, interatomic potentials, MCP, model context protocol",
"author": "ColabFit",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/30/27/630b46d2efdec95da29b67a871764db8b2ba78289860faa7b06c0051a99c/colabfit_mcp-0.0.3.tar.gz",
"platform": null,
"description": "# colabfit-mcp\n\nAn MCP server for interacting with the [ColabFit](https://materials.colabfit.org) database.\n\n## Installation\nDownload source code:\n```\ngit clone https://github.com/colabfit/colabfit-mcp.git\n```\nMake sure the mcp package is installed.\n```\npip install mcp[cli]\n```\nModify your Claude configuration file.\nNavigate to Settings → Developer → Edit Config.\nYour config file should look something like:\n```\n {\n \"mcpServers\": {\n \"colabfit-mcp\": {\n \"command\": \"<path to environment's mcp command>\",\n \"args\": [\n \"run\",\n \"<download-location>/colabfit-mcp/colabfit_mcp.py>\"\n ]\n }\n }\n }\n```\n\n## Functionality\nCurrently, this MCP server will allow clients to query the online ColabFit database and download its dataset files.\n\n## License\nThe ColabFit Tools package is copyrighted by the Regents of the University of\nMinnesota. It can be freely used for educational and research purposes by\nnon-profit institutions and US government agencies only. Other organizations are\nallowed to use the ColabFit Tools package only for evaluation purposes, and any\nfurther uses will require prior approval. The software may not be sold or\nredistributed without prior approval. One may make copies of the software for\ntheir use provided that the copies, are not sold or distributed, are used under\nthe same terms and conditions. As unestablished research software, this code is\nprovided on an \"as is'' basis without warranty of any kind, either expressed or\nimplied. The downloading, or executing any part of this software constitutes an\nimplicit agreement to these terms. These terms and conditions are subject to\nchange at any time without prior notice.\n\n[mcp-name: io.github.colabfit/colabfit-mcp]: # \n\n",
"bugtrack_url": null,
"license": null,
"summary": "A suite of MCP tools for interacting with the ColabFit database",
"version": "0.0.3",
"project_urls": {
"Homepage": "https://github.com/colabfit/colabfit-mcp"
},
"split_keywords": [
"machine learning",
" interatomic potentials",
" mcp",
" model context protocol"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "51c8b9fb3810712e701bbb68faaa5ba9c9a25f7096482551a1b0d16bfc402d11",
"md5": "ebe8ce9258412a56e14f41a6544cdab9",
"sha256": "0e35d847f2508aa718752580ee7f8c3c278420db25f3075b1e5ffaff51a309b0"
},
"downloads": -1,
"filename": "colabfit_mcp-0.0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ebe8ce9258412a56e14f41a6544cdab9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 2069,
"upload_time": "2025-10-16T16:55:12",
"upload_time_iso_8601": "2025-10-16T16:55:12.956292Z",
"url": "https://files.pythonhosted.org/packages/51/c8/b9fb3810712e701bbb68faaa5ba9c9a25f7096482551a1b0d16bfc402d11/colabfit_mcp-0.0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "3027630b46d2efdec95da29b67a871764db8b2ba78289860faa7b06c0051a99c",
"md5": "c2a1fe8f103979f7ecca048567b0ddb6",
"sha256": "799a80726a7dcb88a6959d9018e082132061b3d1a4e125399d8c59892e0ad03e"
},
"downloads": -1,
"filename": "colabfit_mcp-0.0.3.tar.gz",
"has_sig": false,
"md5_digest": "c2a1fe8f103979f7ecca048567b0ddb6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 2155,
"upload_time": "2025-10-16T16:55:14",
"upload_time_iso_8601": "2025-10-16T16:55:14.282002Z",
"url": "https://files.pythonhosted.org/packages/30/27/630b46d2efdec95da29b67a871764db8b2ba78289860faa7b06c0051a99c/colabfit_mcp-0.0.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-16 16:55:14",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "colabfit",
"github_project": "colabfit-mcp",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "colabfit-mcp"
}
JSON
