Cure Cancer With AI MCP

A remote MCP server exposing oncology data including peer-reviewed research, clinical trials, FDA approvals, and IBM MAMMAL biomedical predictions as tools for AI agents.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Cure Cancer With AI

You need:requests authenticate with a free API key (format `ccw_live_...`)Sign in and create a key (shown once at creation)Free tier: 100 requests/hour per key (rolling window)

MCP endpoint (Streamable HTTP)

https://www.curecancerwithai.com/api/mcp

Vendor documentation

What its tools do

15 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (15)

search_oncology
list_research
get_research_paper
list_news
list_blog_posts
get_blog_post
list_fda_approvals
list_clinical_trials
get_clinical_trial
predict_ppi
predict_dti
predict_clintox
search_compounds
list_compound_characteristics
mammal_health

15 of 15 have a description · 0 of 15 declare behavior hints · 13 of 13 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 3:59 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Search oncology research papers and clinical trials
Retrieve FDA-approved oncology drugs and cancer news
Predict protein-protein interactions and drug-target affinity
Assess clinical-trial toxicity using IBM MAMMAL models

Source and maintenance

Community listingRegistry 1.0.0

mcp-registry: io.github.hifarrer/cure-cancer-with-ai@1.0.0 Source repository

Maintenance checked: Nov 6, 2026, 3:51 PM UTC

Protocol and capabilities

Server: cure-cancer-with-ai 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 15 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Tools for the Cure Cancer With AI public API: free oncology data (research papers, news, blog, FDA approvals, clinical trials), a cross-dataset search, and IBM MAMMAL biomedical model predictions (protein–protein, drug–target, ClinTox). Authenticate by sending "Authorization: Bearer ccw_live_YOUR_KEY"; get a free key at https://www.curecancerwithai.com/api-keys.

Tools

15 advertised

search_oncology — Search all oncology datasets

Advertised by the server during the last successful anonymous check.

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.

search_oncology input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "The keyword to search for, e.g. \"osimertinib\"."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Max results per dataset (1–100, default 5)."
    },
    "types": {
      "type": "string",
      "description": "Optional comma-separated datasets to narrow to: research,news,blog,fdaApprovals,clinicalTrials."
    },
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma."
    }
  },
  "additionalProperties": false
}

list_research — List research papers

Advertised by the server during the last successful anonymous check.

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.

list_research input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "to": {
      "type": "string",
      "description": "ISO date upper bound (e.g. 2024-12-31)."
    },
    "from": {
      "type": "string",
      "description": "ISO date lower bound (e.g. 2024-01-01)."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across title and abstract."
    },
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma."
    },
    "treatmentType": {
      "type": "string",
      "description": "Filter by treatment type."
    }
  },
  "additionalProperties": false
}

get_research_paper — Get a research paper

Advertised by the server during the last successful anonymous check.

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

get_research_paper input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "idOrPubmedId"
  ],
  "properties": {
    "idOrPubmedId": {
      "type": "string",
      "description": "Internal id or PubMed id, e.g. \"38123456\"."
    }
  },
  "additionalProperties": false
}

list_news — List cancer news

Advertised by the server during the last successful anonymous check.

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

list_news input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "to": {
      "type": "string",
      "description": "ISO date upper bound (e.g. 2024-12-31)."
    },
    "from": {
      "type": "string",
      "description": "ISO date lower bound (e.g. 2024-01-01)."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across title, summary, and content."
    },
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma."
    }
  },
  "additionalProperties": false
}

list_blog_posts — List blog posts

Advertised by the server during the last successful anonymous check.

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

list_blog_posts input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across title, excerpt, and content."
    },
    "category": {
      "type": "string",
      "description": "Filter by primary category."
    },
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer-type tag."
    }
  },
  "additionalProperties": false
}

get_blog_post — Get a blog post

Advertised by the server during the last successful anonymous check.

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

get_blog_post input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Blog post slug, e.g. \"immunotherapy-breakthroughs\"."
    }
  },
  "additionalProperties": false
}

list_fda_approvals — List FDA approvals

Advertised by the server during the last successful anonymous check.

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

list_fda_approvals input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "to": {
      "type": "string",
      "description": "ISO date upper bound (e.g. 2024-12-31)."
    },
    "from": {
      "type": "string",
      "description": "ISO date lower bound (e.g. 2024-01-01)."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across drug name, generic name, and indication."
    },
    "cancerType": {
      "type": "string",
      "description": "Filter by cancer type, e.g. lung, breast, prostate, colorectal, melanoma, leukemia, lymphoma."
    }
  },
  "additionalProperties": false
}

list_clinical_trials — List clinical trials

Advertised by the server during the last successful anonymous check.

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

list_clinical_trials input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results per page (1–100, default 20)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip (default 0)."
    },
    "search": {
      "type": "string",
      "description": "Keyword search across title and description."
    },
    "status": {
      "type": "string",
      "description": "Filter by trial status, e.g. RECRUITING."
    },
    "condition": {
      "type": "string",
      "description": "Filter by condition."
    }
  },
  "additionalProperties": false
}

get_clinical_trial — Get a clinical trial

Advertised by the server during the last successful anonymous check.

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

get_clinical_trial input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "nctId"
  ],
  "properties": {
    "nctId": {
      "type": "string",
      "description": "NCT id or internal id, e.g. \"NCT01234567\"."
    }
  },
  "additionalProperties": false
}

predict_ppi — Predict protein–protein interaction

Advertised by the server during the last successful anonymous check.

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.

predict_ppi input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "protein_a",
    "protein_b"
  ],
  "properties": {
    "protein_a": {
      "type": "string",
      "description": "Amino-acid sequence, single-letter codes (ACDEFGHIKLMNPQRSTVWY), no FASTA header."
    },
    "protein_b": {
      "type": "string",
      "description": "Amino-acid sequence, single-letter codes."
    }
  },
  "additionalProperties": false
}

predict_dti — Predict drug–target interaction (pKd)

Advertised by the server during the last successful anonymous check.

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.

predict_dti input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "target_seq",
    "drug_seq"
  ],
  "properties": {
    "drug_seq": {
      "type": "string",
      "description": "Drug structure in SMILES notation."
    },
    "norm_y_std": {
      "type": "number",
      "description": "Optional normalization standard-deviation override."
    },
    "target_seq": {
      "type": "string",
      "description": "Target protein amino-acid sequence (single-letter codes)."
    },
    "norm_y_mean": {
      "type": "number",
      "description": "Optional normalization mean override."
    }
  },
  "additionalProperties": false
}

predict_clintox — Predict clinical-trial toxicity (ClinTox)

Advertised by the server during the last successful anonymous check.

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.

predict_clintox input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "smiles"
  ],
  "properties": {
    "smiles": {
      "type": "string",
      "description": "Compound structure in SMILES notation."
    }
  },
  "additionalProperties": false
}

search_compounds — Search pharmaceutical compounds

Advertised by the server during the last successful anonymous check.

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.

search_compounds input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Max results (1–100, default 20)."
    },
    "examples": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Known drug names to find similar compounds for, e.g. [\"aspirin\",\"ibuprofen\"]. Mutually exclusive with preferences."
    },
    "preferences": {
      "type": "object",
      "description": "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.",
      "additionalProperties": {
        "type": "number",
        "maximum": 4,
        "minimum": -4
      }
    },
    "include_characteristics": {
      "type": "boolean",
      "description": "Include each result’s characteristic scores in the response."
    }
  },
  "additionalProperties": false
}

list_compound_characteristics — List compound characteristics

Advertised by the server during the last successful anonymous check.

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

list_compound_characteristics input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

mammal_health — Check MAMMAL model health

Advertised by the server during the last successful anonymous check.

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.

mammal_health input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

2026-11-06: 1 of 1 checks answered
2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 744 ms
95th percentile latency: 744 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 6, 2026, 3:59 PM UTC · probe · passed · 744 ms · metadata changed · 15 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http cure-cancer-with-ai-mcp https://www.curecancerwithai.com/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add cure-cancer-with-ai-mcp --url https://www.curecancerwithai.com/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable cure-cancer-with-ai-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "cure-cancer-with-ai-mcp": {
      "url": "https://www.curecancerwithai.com/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "cure-cancer-with-ai-mcp": {
      "type": "streamableHttp",
      "url": "https://www.curecancerwithai.com/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start cure-cancer-with-ai-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "cure-cancer-with-ai-mcp": {
      "type": "http",
      "url": "https://www.curecancerwithai.com/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http cure-cancer-with-ai-mcp https://www.curecancerwithai.com/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://www.curecancerwithai.com/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "cure-cancer-with-ai-mcp": {
      "serverUrl": "https://www.curecancerwithai.com/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Cure Cancer With AI MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows