Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

OraFabric Medical Ontology Knowledge Base

REMOTE · ORAFABRIC.COM

Expert-structured medical ontologies, relationships, and evidence for AI research and reasoning.

Available components

+4 this week 79 Trust /100

Last scanned (22 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Health and Science

Trust breakdown (7 categories)

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 Security89
Transport & Reachability100
Schema Quality & AI Usability68
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1124 tokens (~187/item across 6 items; 6 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 Management43
  • Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1
    • Authorization: unverified → fail ▼ security
    • Injection markers: unverified → pass ▲ security
    • HSTS header: unverified → pass ▲ security
    • Transport: fail → pass ▲ security
    • MCP protocol: unverified → fail ▼ functional
    • Endpoint reachability: unreachable → reachable ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • Stability: unverified → 0.30 ▲ functional
  • 16 Nov 26 0
    • Endpoint reachability: reachable → unreachable ▼ security
    • Stability: 0.23 → unverified ▼ security
    • Authorization: fail → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • HSTS header: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Capabilities: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list. functional
  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1
    • Tool “check_relation” rewrote its description, which is the text the model reads security
  • 10 Nov 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.

  • 9 Nov 26 +3
    • Schema quality: pass → fail ▼ functional
    • Tool coverage: 35% → 100% ▲ functional
    • Stability: unverified → 0.03 ▲ functional
    • Schema quality: fair → excellent functional
    • “check_relation” reworded the description of “both_directions” cosmetic
    • “check_relation” reworded the description of “filters” cosmetic
    • “check_relation” reworded the description of “limit” cosmetic
    • “check_relation” reworded the description of “relation” cosmetic
    • “explore_concept” reworded the description of “concept” cosmetic
    • “explore_concept” reworded the description of “direction” cosmetic
    • “explore_concept” reworded the description of “filters” cosmetic
    • “explore_concept” reworded the description of “limit” cosmetic
    • “explore_concept” reworded the description of “relations” cosmetic
    • “get_paper” reworded the description of “include_findings” cosmetic
    • “resolve_concept” reworded the description of “limit” cosmetic
    • “resolve_concept” reworded the description of “name” cosmetic
    • “resolve_concept” reworded the description of “type” cosmetic
    • “retrieve_evidence” reworded the description of “filters” cosmetic
    • “retrieve_evidence” reworded the description of “include_hypotheses” cosmetic
    • “retrieve_evidence” reworded the description of “max_evidence” cosmetic
Diagnostics

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 21 Nov 2026 · Probed https://orafabric.com/api/dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=orafabric.com CN=YE2,O=Let's Encrypt,C=US 17 Oct 2026 15 Jan 2027 ECDSA 256 ECDSA-SHA384 58e6ef3da562058dfccb371cc73b6b2986f
SANs: orafabric.com, www.orafabric.com
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of orafabric.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
orafabric.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="OraFabric developer API", error="invalid_token"

Bearer realm="OraFabric developer API", error="invalid_token"
Header Value
strict-transport-security max-age=31536000

Protected resource metadata

Retrieved No
Problem No resource metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://orafabric.com/api/dev/mcp Verified 200
http (plaintext) http://orafabric.com/api/dev/mcp HTTPS enforced 301 https://orafabric.com/api/dev/mcp
MCP tools · 6 exposed · ~1,015 tokens

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 →

Tool Tokens
check_relation ~245

Evidence for, against and null on one relationship between two named things. $0.03. A finding is returned only when one end matches the subject and the other matches the object. If a name matches several concepts, results include all of them and notices lists their ids.

NameTypeReqDescription
both_directionsboolean–Also return evidence for the reverse relationship, object acting on subject. Set it when the direction of causation is itself the question, because the literature often reports both.
filtersobject–Narrow the evidence before it is returned. Filtering here is better than filtering the result afterwards, because the retrieval budget is then spent on evidence that qualifies.
limitinteger–How many findings to return per bucket. Raise it for a well-studied pair where 20 may only surface the most recent work.
objectstringyesThe thing acted on.
relationstring–The specific claim to test. Use 'any' unless the question names a direction of effect. 'any' returns supporting, contradicting and null evidence across all relation types, which is usually more infor…
subjectstringyesThe acting thing.

No output schema declared.

No examples provided.

explore_concept ~291

What is known around one gene, drug or disease: upstream, downstream and associations. $0.03.

NameTypeReqDescription
conceptstringyesOne gene, drug or disease to walk outward from. A single entity, not a question. Use retrieve_evidence for a question. If the name may be ambiguous, resolve it first with the free resolve_concept.
directionstring–Which way to walk. 'downstream' returns what this concept acts on: what it causes, inhibits or treats. 'upstream' returns what acts on it: what regulates, inhibits or induces it. 'both' returns each…
filtersobject–Narrow the evidence before it is returned. Filtering here is better than filtering the result afterwards, because the retrieval budget is then spent on evidence that qualifies.
limitinteger–How many relationships to return per direction. Raise it for a hub concept such as TP53 or EGFR, where 20 will only show the most common edges.
relationsarray–Restrict the walk to these relation types. Use it when the question is about one kind of link, ['inhibits','activates'] for regulation, ['treats','prevents'] for therapeutic claims. Leaving it unset…

No output schema declared.

No examples provided.

get_coverage ~27

What the knowledge base currently covers: datasets, concepts and relationships. Free. No arguments.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_paper ~92

One paper and the findings extracted from it. Does not return the article text. $0.03.

NameTypeReqDescription
idstringyesA paper_id from an earlier result, a PMID or a DOI.
include_findingsboolean–Return the findings extracted from this paper, not only its metadata. Turn it off when you only need the title, journal and year, for example when rendering a citation.

No output schema declared.

No examples provided.

resolve_concept ~163

Match a name, abbreviation or synonym to standard concepts. Free.

NameTypeReqDescription
limitinteger–How many candidate concepts to return. Raise it when the name is a common abbreviation likely to collide; 5 is enough for a specific name.
namestringyesThe name, abbreviation or synonym to resolve, as it appeared in the question. Do not normalise it first. 'HER2', 'ERBB2' and 'Her-2/neu' are all valid input.
typestring–Restrict to concepts of this kind. Set it when the name is ambiguous across kinds. 'CD20' is both a gene and a drug target, 'ALK' is a gene and a disease qualifier. Leave unset to see every kind.

No output schema declared.

No examples provided.

retrieve_evidence ~197

Search the whole knowledge base for a research question. Returns an evidence pack: findings, a subgraph and the papers. $0.03. The model writes the answer.

NameTypeReqDescription
filtersobject–Narrow the evidence before it is returned. Filtering here is better than filtering the result afterwards, because the retrieval budget is then spent on evidence that qualifies.
include_hypothesesboolean–Include author interpretations and hypotheses alongside observed findings, returned in a separate bucket. Keep it on when the question is about mechanism; turn it off when you need only what was meas…
max_evidenceinteger–How many findings to retrieve. Lower it to around 20 for a narrow factual question; raise it towards 100 when the question spans several mechanisms or you are looking for contradictions, which only a…
querystringyesThe research question, up to 1,000 characters.

No output schema declared.

No examples provided.

Install

How do I install the OraFabric Medical Ontology Knowledge Base MCP server?

OraFabric Medical Ontology Knowledge Base is a hosted endpoint at https://orafabric.com/api/dev/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 · orafabric.com

# add to Claude Code
claude mcp add --transport http com-orafabric-medical-ontology 'https://orafabric.com/api/dev/mcp'
Common questions

What is the OraFabric Medical Ontology Knowledge Base MCP server?

OraFabric Medical Ontology Knowledge Base is an MCP server listed in the public MCP registry as com.orafabric/medical-ontology. Expert-structured medical ontologies, relationships, and evidence for AI research and reasoning. This page covers its hosted endpoint (https://orafabric.com/api/dev/mcp).

Is the OraFabric Medical Ontology Knowledge Base MCP server safe to use?

OraFabric Medical Ontology Knowledge Base scores 79 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 OraFabric Medical Ontology Knowledge Base MCP server expose?

OraFabric Medical Ontology Knowledge Base exposes 6 tools: retrieve_evidence, check_relation, explore_concept, get_paper, resolve_concept, get_coverage. Their descriptions and schemas cost roughly 1,015 tokens of context every time the server is loaded.

Does the OraFabric Medical Ontology Knowledge Base MCP server require authentication?

Yes. OraFabric Medical Ontology Knowledge Base asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the OraFabric Medical Ontology Knowledge Base MCP server still maintained?

OraFabric Medical Ontology Knowledge Base is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the OraFabric Medical Ontology Knowledge Base MCP server?

VerifyMCP ran 13 checks on OraFabric Medical Ontology Knowledge Base, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.