OpenCancer
REMOTE · OPENCANCER.AI
Cancer patient expert: NCCN-grounded answers with sources, recruiting trials, and expert review.
Available components
Last scanned (3 hours ago)
Scores higher than 73% of remote servers
Reachable. Last reached 25 Oct 2026.
Category Health and Science
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 924 tokens (~184/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
- Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 93% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “ask_opencancer” rewrote its description, which is the text the model reads security
- Tool “find_clinical_trials” rewrote its description, which is the text the model reads security
- Tool “get_trial_details” rewrote its description, which is the text the model reads security
- Tool “open_case” rewrote its description, which is the text the model reads security
- Schema quality: 241 → 184 ▲ functional
- Stability: unverified → 0.03 ▲ functional
- “find_clinical_trials” reworded the description of “location” cosmetic
- “send_feedback” reworded the description of “answer_id” cosmetic
- 15 Oct 26 72
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 25 Oct 2026 · Probed https://opencancer.ai/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=opencancer.ai | CN=YR1,O=Let's Encrypt,C=US | 1 Oct 2026 | 30 Dec 2026 | RSA 2048 | SHA256-RSA | 6bec6dc980a1feeb1a93a3f83d7717175d7 |
| SANs: opencancer.ai | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of opencancer.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| opencancer.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://opencancer.ai/api/mcp | Verified | 200 | |
| http (plaintext) | http://opencancer.ai/api/mcp | HTTPS enforced | 308 | https://opencancer.ai/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
ask_opencancer Ask OpenCancer ~220
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 disclaimer, a link to OpenCancer's care team, and an answer id. Emergencies, prognosis or life-expectancy questions, and questions about children return a safety message that routes to the care team instead of an answer. Educational information, not medical advice. Accepts no personal identifiers
| Name | Type | Req | Description |
|---|---|---|---|
| cancer_type | string | – | Optional cancer type, to focus the guidelines used, e.g. "colon cancer". |
| context | string | – | Optional general context such as stage or treatments tried, e.g. "stage 3, finished FOLFOX". No identifiers. |
| question | string | yes | The question in plain language, in the user's language, without personal identifiers. |
| Name | Type | Req | Description |
|---|---|---|---|
| answer | string | yes | – |
| answer_id | string|null | yes | – |
| care_team_url | string | yes | – |
| disclaimer | string | yes | – |
| grounding | object | – | – |
| needs_human_review | boolean | yes | – |
| review_status | string | yes | – |
| sources | array | yes | – |
No examples provided.
find_clinical_trials Find recruiting clinical trials ~212
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 for a specific case. Listing a trial is not an eligibility decision; only the trial team can confirm eligibility
| Name | Type | Req | Description |
|---|---|---|---|
| condition | string | yes | Cancer type or condition, e.g. "pancreatic cancer". |
| keyword | string | – | Optional biomarker, drug, or treatment, e.g. "KRAS G12C" or "CAR-T". |
| location | string | – | Optional city, state, or country, e.g. "Boston" or "Germany" (city level, not a street address). |
| phase | string | – | Optional trial phase. |
| Name | Type | Req | Description |
|---|---|---|---|
| expert_help_url | string | yes | – |
| search_url | string | yes | – |
| total | number | yes | – |
| trials | array | yes | – |
No examples provided.
get_trial_details Get clinical trial details ~93
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
| Name | Type | Req | Description |
|---|---|---|---|
| nct_id | string | yes | ClinicalTrials.gov ID, e.g. "NCT05902169". |
| Name | Type | Req | Description |
|---|---|---|---|
| ages | string | – | – |
| conditions | array | – | – |
| contacts | array | – | – |
| exclusion_criteria | string | – | – |
| expert_help_url | string | yes | – |
| inclusion_criteria | string | – | – |
| interventions | array | – | – |
| last_updated | string | – | – |
| nct_id | string | yes | – |
| official_title | string | – | – |
| phase | string | – | – |
| sex | string | – | – |
| site_count | number | – | – |
| sites | array | – | – |
| sponsor | string | – | – |
| status | string | yes | – |
| summary | string | – | – |
| title | string | yes | – |
| url | string | yes | – |
No examples provided.
open_case Get the expert review link ~131
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.
| Name | Type | Req | Description |
|---|---|---|---|
| cancer_type | string | – | Optional cancer type, e.g. "prostate cancer". |
| preferred_destinations | array | – | – |
| question | string | – | Optional: what the patient wants experts to look at, without personal identifiers. |
| Name | Type | Req | Description |
|---|---|---|---|
| available_intake_destinations | array | – | – |
| case_created | boolean | yes | – |
| consent_required | boolean | yes | – |
| intake_url | string | yes | – |
| message | string | yes | – |
| preferred_destinations | array | – | – |
No examples provided.
send_feedback Flag an answer or send feedback ~193
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 message). Feedback is read by the OpenCancer team; it is not an urgent-care channel and no reply is sent through it.
| Name | Type | Req | Description |
|---|---|---|---|
| answer_id | string | – | Optional. The answer id from an OpenCancer answer. |
| kind | string | yes | wrong_or_unsafe, missing_answer, bug, idea, or praise. |
| message | string | – | Optional. The user's feedback in their own words. Contact details are not accepted. |
| tool | string | – | Optional. Which OpenCancer tool this is about. |
| Name | Type | Req | Description |
|---|---|---|---|
| duplicate | boolean | – | – |
| in_review_queue | boolean | yes | – |
| saved | boolean | yes | – |
No examples provided.
How do I install the OpenCancer MCP server?
OpenCancer is a hosted endpoint at https://opencancer.ai/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · opencancer.ai
claude mcp add --transport http ai-opencancer-opencancer 'https://opencancer.ai/api/mcp'
What is the OpenCancer MCP server?
OpenCancer is an MCP server listed in the public MCP registry as ai.opencancer/opencancer. Cancer patient expert: NCCN-grounded answers with sources, recruiting trials, and expert review. This page covers its hosted endpoint (https://opencancer.ai/api/mcp).
Is the OpenCancer MCP server safe to use?
OpenCancer scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the OpenCancer MCP server expose?
OpenCancer exposes 5 tools: ask_opencancer, find_clinical_trials, get_trial_details, open_case, send_feedback. Their descriptions and schemas cost roughly 849 tokens of context every time the server is loaded.
Does the OpenCancer MCP server require authentication?
No. We connected to OpenCancer without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the OpenCancer MCP server still maintained?
OpenCancer is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.