Cure Cancer With AI

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Cure Cancer With AI": {
      "url": "https://www.curecancerwithai.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (15)

• 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:

  • q (required) — string — The keyword to search for, e.g. "osimertinib".
  • limit — integer — Max results per dataset (1–100, default 5).
  • types — string — Optional comma-separated datasets to narrow to: research,news,blog,fdaApprovals,clinicalTrials.
  • cancerType — string — Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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:

  • to — string — ISO date upper bound (e.g. 2024-12-31).
  • from — string — ISO date lower bound (e.g. 2024-01-01).
  • limit — integer — Results per page (1–100, default 20).
  • offset — integer — Number of results to skip (default 0).
  • search — string — Keyword search across title and abstract.
  • cancerType — string — Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma.
  • treatmentType — string — Filter by treatment type.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_research_paper

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

  Parameters:

  • idOrPubmedId (required) — string — Internal id or PubMed id, e.g. "38123456".

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_news

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

  Parameters:

  • to — string — ISO date upper bound (e.g. 2024-12-31).
  • from — string — ISO date lower bound (e.g. 2024-01-01).
  • limit — integer — Results per page (1–100, default 20).
  • offset — integer — Number of results to skip (default 0).
  • search — string — Keyword search across title, summary, and content.
  • cancerType — string — Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_blog_posts

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

  Parameters:

  • limit — integer — Results per page (1–100, default 20).
  • offset — integer — Number of results to skip (default 0).
  • search — string — Keyword search across title, excerpt, and content.
  • category — string — Filter by primary category.
  • cancerType — string — Filter by cancer-type tag.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_blog_post

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

  Parameters:

  • slug (required) — string — Blog post slug, e.g. "immunotherapy-breakthroughs".

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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:

  • to — string — ISO date upper bound (e.g. 2024-12-31).
  • from — string — ISO date lower bound (e.g. 2024-01-01).
  • limit — integer — Results per page (1–100, default 20).
  • offset — integer — Number of results to skip (default 0).
  • search — string — Keyword search across drug name, generic name, and indication.
  • cancerType — string — Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_clinical_trials

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

  Parameters:

  • limit — integer — Results per page (1–100, default 20).
  • offset — integer — Number of results to skip (default 0).
  • search — string — Keyword search across title and description.
  • status — string — Filter by trial status, e.g. RECRUITING.
  • condition — string — Filter by condition.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_clinical_trial

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

  Parameters:

  • nctId (required) — string — NCT id or internal id, e.g. "NCT01234567".

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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:

  • protein_a (required) — string — Amino-acid sequence, single-letter codes (ACDEFGHIKLMNPQRSTVWY), no FASTA header.
  • protein_b (required) — string — Amino-acid sequence, single-letter codes.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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:

  • target_seq (required) — string — Target protein amino-acid sequence (single-letter codes).
  • drug_seq (required) — string — Drug structure in SMILES notation.
  • norm_y_std — number — Optional normalization standard-deviation override.
  • norm_y_mean — number — Optional normalization mean override.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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:

  • smiles (required) — string — Compound structure in SMILES notation.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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:

  • limit — integer — Max results (1–100, default 20).
  • examples — array — Known drug names to find similar compounds for, e.g. ["aspirin","ibuprofen"]. Mutually exclusive with preferences.
  • preferences — object — 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.
  • include_characteristics — boolean — Include each result’s characteristic scores in the response.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.