MCP.Market

HLA-Verify MCP server

online · 100% uptime
by hlaverify.com·com.hlaverify/hla-verify·v1.0.1
No reviews yet

HLA nomenclature and match checks against a pinned IPD-IMGT/HLA release. No patient identifiers.

A88/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed HLA-Verify yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

HLA-Verify tools (10, 1 write)

write = sends, deletes, buys or posts
  • aboutFree

    What this server is and is not, what to send it, benchmark evidence for why to use it, the beta state, and terms.

  • allele_infoFree

    Look up one exact name in the pinned release and return what it is: assigned (G/P group, first release, confirmed status, WMDA serology, null flag), valid_prefix (member count and sample), or deleted (successor). Not found if the name has never existed in any release.

  • beta_signupwrite actionFree

    Put a user on the free public beta's notification list for paid API keys. Ask before calling: it records the address they give you. Re-signing the same address is safe (status already_recorded). Someone who needs a higher rate limit today should email hello@hlaverify.com for a beta key instead of waiting.

  • check_typingFree

    QC-check one HLA typing (all loci) against the pinned release: resolves every reported allele, flags unresolvable/outdated/locus-mismatched/null alleles, flags too-many/single/homozygous per locus, computes the B-leader (-21 M/T) and KIR-ligand (C1/C2/Bw4) profile, and DRB3/4/5 expected-vs-reported. Nomenclature and internal-consistency checking of the report, not clinical interpretation. typing: {"A": ["A*01:01", "A*02:01"], "B": [...], "DRB1": [...], ...} (any nomenclature era; allele strings only, no patient identifiers).

  • donor_compatFree

    Donor/recipient immunogenetic compatibility under two published rule sets: HLA-B leader match (-21 M/T, Petersdorf 2020) for a single HLA-B mismatch, and KIR ligand (C1/C2/Bw4) class comparison, computed over each side's full typing QC. Rule checking against published frameworks; it does not rank or recommend a donor. recipient/donor: {"A": [...], "B": [...], "C": [...], "DRB1": [...], ...} (allele strings only, no patient identifiers). Decision support only; not a medical device.

  • match_scoreFree

    Count a donor-recipient HLA match by the published counting rules (R1-R6): allele arithmetic over chromosomes, not a donor recommendation. recipient/donor: {"A": ["A*01:01","A*02:01"], "B": [...], ...} (two reported alleles per locus, any nomenclature era; allele strings only, no patient identifiers). framework: 6/6, 8/8, 10/10, 12/12, or antigen. Returns count, per-locus verdicts, GvH/HvG mismatch counts, and flags; unresolvable typing yields 'potential', never a confident count.

  • normalize_alleleFree

    Normalize one reported HLA allele name (any era) to current 2-field form, with G group, P group, serologic equivalent, and flags.

  • research_accessFree

    Apply for free HLA-Verify access for an academic or nonprofit lab. Ask before calling: it records the address, institution and use case you give it. Approval is manual: a person reads every application, so it is not instant and not guaranteed. If it is approved the applicant is emailed a single-use code that takes 100% off a subscription for 12 months at self-serve checkout, with no card and no contract. Re-applying with the same address is safe (status already_recorded) and never overwrites an application that has already been decided. Commercial labs should buy a tier at https://api.hlaverify.com/pricing instead.

  • validate_gl_stringFree

    Validate and normalize a GL String (Genotype List, ^ | + ~ / grammar): resolves every allele token, flags outdated/unresolvable names and structural problems (mixed loci within a slash-list, a repeated locus within a haplotype or across ^ blocks, more than two haplotypes, differing loci across a genotype or genotype list, empty elements), and returns the normalized string. Grammar and nomenclature checking only; send allele names, not patient identifiers.

  • verify_textFree

    Scan HLA typing report text, or model output about HLA, for allele-shaped tokens and classify each one: valid / legacy (with modern form) / deleted (with successor) / fabricated. Nomenclature checking against a pinned IPD-IMGT/HLA release, not interpretation of a case. Use on any AI-generated or transcribed content mentioning HLA. Send the HLA content only, with patient identifiers removed first.

Public scan report

scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 220ms20/20
  • Tool poisoning10 tool descriptions checked15/15
  • Auth qualityAPI key sent as a header8/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How HLA-Verify compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 48,255 servers
Tools
10
the typical server has 7
Tools that change things
10%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
99 ms
faster than 84% of 30,031 servers

What its tools let an agent do: 9 read · 1 change

Install HLA-Verify in Claude Code, Cursor or VS Code

claude mcp add --transport http hla-verify https://api.hlaverify.com/mcp
Add to Cursor

What the publisher says

From the HLA-Verify repository's README, as published. We do not edit it. Read it on GitHub

verifiable-science-envs

Deterministic, executable-oracle RL environments and evaluation suites for clinical genomics — starting with HLA/immunogenetics.

Every answer is computed from the pinned IPD-IMGT/HLA release's own files. No human labels, no frequency data, no licensed tables — so the grader is auditable line-by-line, the sealed split regenerates on every release, and a model cannot have memorized the post-cutoff tasks.

The benchmarks

Working on this repo? Read CLAUDE.md first: a push to main deploys production, and the project's status, decisions and runbook live in the private portfolio hub rather than here.

Headline findings so far: every model family tested (Claude, Qwen, Mistral, Llama, Phi, Gemma) scores 0% on 2-field ambiguity expansion (0 of 30 tasks per model on the full 550-task suite), the core clinical trap; models fabricate allele names at 0.06–0.20 per task, and the anthropic/claude-sonnet-4-6 figure of 0.09 is a lower bound because 187 of its 550 responses were truncated and graded malformed; on matching, the naive string baseline falls from 28% (family A) to 0%, and open models reach 0–14% because they count matched loci instead of chromosomes. Full tables with Wilson CIs on the bench pages; current state in the bench pages below.

Every headline figure above is recomputed from the committed run artifacts in bench/reproduce.ipynb, which prints the published number next to the recomputed one with a pass or fail for each claim. It needs no API key and no local checkout.

HLA-Verify — the graders as an API

The same engine as a verification service (no LLM, no storage): POST /v1/verify checks every allele-shaped token in free text against the pinned release (fabricated / deleted-with-successor / legacy / valid, with G groups and flags); POST /v1/normalize fixes typing reports; GET /v1/allele/ returns the facts; POST /v1/match scores a donor–recipient pair under the published rules R1–R6.

Hosted, live: api.hlaverify.com (also https://hlaverify.com/v1/…). Open for evaluation at 100 calls a day per IP (60 requests/minute, up to 250 typings per /v1/normalize call); keyed access for labs, LIMS vendors and agent platforms with higher daily quotas and larger batches (hello@hlaverify.com). Quotas reset at UTC midnight and every billable response carries x-hla-verify-daily-limit, -daily-remaining and -daily-reset.

curl -s https://api.hlaverify.com/v1/verify -H 'content-type: application/json' \
  -d '{"text": "A*0101, B*15:504:01, DQB1*05:03:26:99"}'

The hosted API is a Cloudflare Worker (edge/) that looks names up in tables exported from the pinned release by this repository's Python engine (python -m scienvs.service.edgeexport); a golden test (edge/test/) proves the Worker's output is byte-identical to the Python service on thousands of generated inputs. Self-hosted Python service:

pip install -e ".[service]" && uvicorn sci_envs.service.app:app

Live demo (runs entirely in your browser — typing data never leaves your machine): hlaverify.com/demo · mirrored on Hugging Face: Spaces/jason-brelsford/hla-verify

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

HLA-Verify: common questions

Is HLA-Verify MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the HLA-Verify safety report
How do I install HLA-Verify?
It runs remotely at api.hlaverify.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does HLA-Verify need an API key?
Yes. The registry entry asks for X-API-Key.
Is HLA-Verify maintained?
The last commit was 34 days ago (2026-10-01). The latest release is v1.0.1.
Is HLA-Verify up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does HLA-Verify compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,255 servers); tools 10 (the typical server has 7); tools that change things 10% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.