imaging-data-commons
Queries and downloads public cancer imaging data from NCI Imaging Data Commons
by k-dense-aiFree
Description
imaging-data-commons is an agent skill for querying and downloading public cancer imaging data from the National Cancer Institute Imaging Data Commons, known as IDC. It covers collection discovery, DICOM access, and radiology data such as CT, MR and PET scans. Data access needs no login. The skill explains that IDC metadata can be reached in three ways: a bundled local DuckDB index that works offline after installation, the hosted IDC service over MCP or REST, and additional indices and clinical tables fetched from GitHub and S3. File downloads come from public Google Cloud Storage and AWS S3 buckets. DICOMweb access can use the public IDC proxy, which needs no authentication, or the Google Cloud Healthcare API, which needs Google Cloud credentials. Optional BigQuery queries also need Google Cloud authentication, and citation resolution contacts DOI services. The skill says to choose the access path first, because the cheapest correct route depends on the session and the task. It records that it was reviewed on 30 September 2026 against idc-index 0.12.5, idc-index-data 24.2.2, IDC v24 and hosted API 3.0.0b3, and it asks you to recheck at the time of use.…
Highlights
- Query and download public cancer imaging data
- CT, MR and PET radiology collections
- Offline local DuckDB index
- Public DICOMweb proxy with no login
- Google Cloud access only where needed
Ratings & Reviews
No ratings yet
Be the first to rate imaging-data-commons.
People also visit
imaging-data-commons FAQ
What data does it access?
Public cancer imaging collections from the NCI Imaging Data Commons, including CT, MR and PET data in DICOM format.
Do I need an account?
No login is needed for data access. Some options, such as the Google Cloud Healthcare API and BigQuery queries, need Google Cloud authentication.
Does it work offline?
Partly. A bundled local DuckDB index works offline after installation, though some indices and tables are fetched from GitHub or S3.
How should I pick an access path?
The skill says there is no single default. The cheapest correct path depends on the session and the task.
How do I install it?
Run npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill imaging-data-commons.
Is it checked for security?
Its security audits show passes from Gen Agent Trust Hub, Socket and Snyk.
What are the best imaging-data-commons alternatives?
Popular alternatives to imaging-data-commons include cellxgene-census, depmap and pydicom. See all imaging-data-commons alternatives