io.github.hifarrer/cure-cancer-with-ai

Official15 tools

by hifarrer

Cure Cancer With AI

Free oncology data (research, trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions.

Access oncology research, trials, FDA approvals and IBM biomedical predictions for cancer research.

Captured live from the server via tools/list.

search_oncology

Search a keyword across every Cure Cancer With AI dataset at once — research papers, news, blog posts, FDA approvals, and clinical trials — with results grouped by type. Use this first for broad discovery, then fetch a single record by id/slug/nctId for full detail.

Parameters (4)

qstringrequired
The keyword to search for, e.g. "osimertinib".
typesstring
Optional comma-separated datasets to narrow to: research,news,blog,fdaApprovals,clinicalTrials.
cancerTypestring
Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma.
limitinteger
Max results per dataset (1–100, default 5).

list_research

List peer-reviewed oncology research papers ingested from PubMed (abstracts, authors, journal, plain-language summaries). Filter by cancer type, treatment type, keyword, or publication date.

Parameters (7)

cancerTypestring
Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma.
treatmentTypestring
Filter by treatment type.
searchstring
Keyword search across title and abstract.
fromstring
ISO date lower bound (e.g. 2024-01-01).
tostring
ISO date upper bound (e.g. 2024-12-31).
limitinteger
Results per page (1–100, default 20).
offsetinteger
Number of results to skip (default 0).

get_research_paper

Fetch a single research paper by its internal id or PubMed id.

Parameters (1)

idOrPubmedIdstringrequired
Internal id or PubMed id, e.g. "38123456".

list_news

List curated cancer news articles aggregated from trusted sources. Filter by cancer type, keyword, or published date.

Parameters (6)

cancerTypestring
Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma.
searchstring
Keyword search across title, summary, and content.
fromstring
ISO date lower bound (e.g. 2024-01-01).
tostring
ISO date upper bound (e.g. 2024-12-31).
limitinteger
Results per page (1–100, default 20).
offsetinteger
Number of results to skip (default 0).

list_blog_posts

List editorial blog articles (excerpts). Use get_blog_post for full content. Filter by category, cancer-type tag, or keyword.

Parameters (5)

categorystring
Filter by primary category.
cancerTypestring
Filter by cancer-type tag.
searchstring
Keyword search across title, excerpt, and content.
limitinteger
Results per page (1–100, default 20).
offsetinteger
Number of results to skip (default 0).

get_blog_post

Fetch a single blog post by slug, including the full article content.

Parameters (1)

slugstringrequired
Blog post slug, e.g. "immunotherapy-breakthroughs".

list_fda_approvals

List FDA-approved oncology drugs with indication, company, approval date, and label links. Filter by cancer type, keyword, or approval date.

Parameters (6)

cancerTypestring
Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma.
searchstring
Keyword search across drug name, generic name, and indication.
fromstring
ISO date lower bound (e.g. 2024-01-01).
tostring
ISO date upper bound (e.g. 2024-12-31).
limitinteger
Results per page (1–100, default 20).
offsetinteger
Number of results to skip (default 0).

list_clinical_trials

List clinical trials from public registries (conditions, status, intervention type). Filter by condition, status (e.g. RECRUITING), or keyword.

Parameters (5)

conditionstring
Filter by condition.
statusstring
Filter by trial status, e.g. RECRUITING.
searchstring
Keyword search across title and description.
limitinteger
Results per page (1–100, default 20).
offsetinteger
Number of results to skip (default 0).

get_clinical_trial

Fetch a single clinical trial by NCT id (or internal id), including eligibility criteria and locations.

Parameters (1)

nctIdstringrequired
NCT id or internal id, e.g. "NCT01234567".

predict_ppi

Predict the binding-affinity class for a pair of proteins using the IBM MAMMAL biomedical foundation model. Returns label "1" (interacting) or "0" (non-interacting). Inference is CPU-bound and may take up to ~60s.

Parameters (2)

protein_astringrequired
Amino-acid sequence, single-letter codes (ACDEFGHIKLMNPQRSTVWY), no FASTA header.
protein_bstringrequired
Amino-acid sequence, single-letter codes.

predict_dti

Predict drug–target binding affinity as pKd (−log10 Kd; higher = stronger binding) using IBM MAMMAL. Inference is CPU-bound and may take up to ~60s.

Parameters (4)

target_seqstringrequired
Target protein amino-acid sequence (single-letter codes).
drug_seqstringrequired
Drug structure in SMILES notation.
norm_y_meannumber
Optional normalization mean override.
norm_y_stdnumber
Optional normalization standard-deviation override.

predict_clintox

Predict clinical-trial toxicity for a compound using IBM MAMMAL. Returns pred 1 (toxic / likely to fail trials) or 0 (not toxic) plus a raw score. Inference is CPU-bound and may take up to ~60s.

Parameters (1)

smilesstringrequired
Compound structure in SMILES notation.

search_compounds

Find pharmaceutical compounds two ways: by example drugs you already know (fuzzy-matched), or by setting target characteristics on a −4…+4 scale. Provide exactly one of `examples` or `preferences`. Use list_compound_characteristics for the available preference names.

Parameters (4)

examplesarray
Known drug names to find similar compounds for, e.g. ["aspirin","ibuprofen"]. Mutually exclusive with preferences.
preferencesobject
Map of characteristic name to desired value on the −4…+4 scale, e.g. {"Neuroactive":3,"Immunoactive":-2}. Omit a characteristic to ignore it. Mutually exclusive with examples.
limitinteger
Max results (1–100, default 20).
include_characteristicsboolean
Include each result’s characteristic scores in the response.

list_compound_characteristics

List the pharmaceutical-compound characteristics (each scored on the −4…+4 scale) that can be used as preference keys in search_compounds.

No parameters.

mammal_health

Check whether the IBM MAMMAL prediction model is loaded and ready. No API key required. Call this before predict_* tools if a prior prediction timed out.

No parameters.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "cure-cancer-with-ai": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://www.curecancerwithai.com/api/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.