OpenCancer

ai.opencancer/opencancer

Cancer patient expert: NCCN-grounded answers with sources, recruiting trials, and expert review.

Yes, your AI can use this right now.Answered a live MCP handshake in 447 ms with no sign-in needed and exposes 5 tools.

Connect it

Settings → Connectors → Add custom connector
URL: https://opencancer.ai/api/mcp

5 tools, verified live

Pulled straight from the server with tools/list on 2026-10-18.
ask_opencancerread-only

Answers a cancer patient or caregiver question in plain language, grounded in NCCN Guidelines for Patients and medical literature. Covers what a diagnosis, stage, biomarker or test result means; treatment options; side effects and their management; questions for the oncologist; second opinions; living with cancer. Answers in the language of the question. Returns the answer, its sources, a disclaim

find_clinical_trialsread-only

Lists clinical trials recruiting now for a cancer type, from ClinicalTrials.gov, optionally near a city, state or country and filtered by a biomarker, drug or treatment keyword and by phase. Returns up to 8 trials with NCT number, phase, sponsor, the sites closest to the requested place, a registry link, a link to the full search, and a link to an OpenCancer expert who can build a trial shortlist

get_trial_detailsread-only

Returns one clinical trial from ClinicalTrials.gov by its NCT number: what it tests, phase, status, last registry update, ages, the inclusion and exclusion criteria in their original wording, recruiting sites with their status, study contacts, and the registry link. Eligibility is confirmed only by the study team

open_caseread-only

Returns a link where a patient can start an expert review of their case by OpenCancer and Cancer Commons scientists (records, options, trial shortlist, next step). The link only opens an intake page: no case is created and no records are sent. The patient enters their own details and personally confirms consent on that page. Accepts no names, contact details or records.

send_feedback

Flags an OpenCancer answer for human expert review, or sends feedback to the OpenCancer team. Used when the user says an OpenCancer answer was wrong, unsafe, or incomplete, or wants to tell OpenCancer something (answer_id identifies the answer; message holds the user's words). Also used to report that an OpenCancer tool returned no usable answer (kind "missing_answer" with answer_id or tool, no me

Alternatives in AI & Agents

Compare →
Try “Notion”, “Stripe”, “create invoice”, “browser”