Folklore Clinical Variant Interpretation MCP
REMOTE · API.HELENA.BIO
ACMG/AMP germline variant classification, gene profiles, disease associations and literature.
Available components
Last scanned (1 hour ago)
Scores higher than 84% of remote servers
Reachable. Last reached 5 Nov 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 Security66
- 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 enforcement could not be verified: the plaintext port answered with HTTP 404, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability80
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1689 tokens (~140/item across 12 items; 11 tools + 1 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 Management86
- Stability check failed: schema churn in the 30 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 5 additions. See how to fix → Fail
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
- 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
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
- Supports UI / widget rendering.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.
- 1 Nov 26 −2
- Stability: pass → fail ▼ security
- Tool “search_variant_evidence” was removed ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “get_gene_disease_associations” rewrote its description, which is the text the model reads security
- Tool “get_gene_profile” rewrote its description, which is the text the model reads security
- Tool “get_gene_section” rewrote its description, which is the text the model reads security
- Tool “get_publication_details” rewrote its description, which is the text the model reads security
- Tool “resolve_gene” rewrote its description, which is the text the model reads security
- Tool “search_disease_genes” rewrote its description, which is the text the model reads security
- Tool “search_gene_literature” rewrote its description, which is the text the model reads security
- Tool “search_literature_corpus” rewrote its description, which is the text the model reads security
- Tool “search_variant_literature” rewrote its description, which is the text the model reads security
- Tool “support_helena” rewrote its description, which is the text the model reads security
- Prompt “review_vus_evidence” was removed ▼ functional
- Resource “folklore-variant-evidence-view” was removed ▼ functional
- Schema quality: 209 → 140 ▲ functional
- Schema quality: excellent → good functional
- New prompt “assess_vus” functional
- New resource “folklore-variant-classification-view” functional
- Server version: 1.6.0 → 1.7.0 functional
- New tool “classify_germline_variant” functional
- “get_gene_disease_associations” reworded the description of “gene” cosmetic
- “resolve_gene” reworded the description of “query” cosmetic
- “search_disease_genes” reworded the description of “disease” cosmetic
- Tool “get_gene_profile” changed its title: Read the complete public gene evidence profile → Read the complete gene profile cosmetic
- Tool “get_gene_section” changed its title: Read a page of source-qualified gene evidence → Read a page of gene records cosmetic
- 30 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 1621 → 2515 ▼ functional
- Server version: 1.5.0 → 1.6.0 functional
- New tool “get_gene_profile” functional
- New tool “get_gene_section” functional
- New tool “resolve_gene” functional
- New tool “search_gene_literature” functional
- 22 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “search_variant_evidence” rewrote its description, which is the text the model reads security
- 10 Oct 26 +49
- Authorization: unverified → partial ▲ security
- Injection markers: unverified → pass ▲ security
- Stability: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- 7 Oct 26 −49
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Authorization: partial → unverified ▼ security
- Schema quality: 100 → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 11 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “search_variant_evidence” rewrote its description, which is the text the model reads security
- Schema quality: 1061 → 1484 ▼ functional
- Server version: 1.4.2 → 1.5.0 functional
- New tool “get_gene_disease_associations” functional
- New tool “search_disease_genes” functional
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 5 Nov 2026 · Probed https://api.helena.bio/folklore/v1/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_256_GCM_SHA384 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.helena.bio | CN=YE2,O=Let's Encrypt,C=US | 29 Sept 2026 | 28 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 6b9210a8b41dd3d82604250e423d06961d7 |
| SANs: api.helena.bio | ||||||
| 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 secure
Validation of api.helena.bio. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| bio. | present | 5606 | 8 | Verified |
| helena.bio. | present | 17027 | 13 | Verified |
| api.helena.bio. | Verified address RRset verified with the apex keys |
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 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.helena.bio/folklore/v1/mcp | Verified | 200 | |
| http (plaintext) | http://api.helena.bio/folklore/v1/mcp | Inconclusive | 404 |
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 →
classify_germline_variant Classify or interpret a germline variant under ACMG/AMP ~175
Classify one GRCh38 germline nuclear SNV or simple indel smaller than 50 bp under ACMG/AMP. Accepts genomic, coding or protein HGVS, coordinates, SPDI, rsID or a returned canonical key. Returns normalized identity, automated classification, applied criteria, ClinVar assertions, population frequencies, annotations and source provenance when available. Ambiguous input returns candidates for selection.
| Name | Type | Req | Description |
|---|---|---|---|
| assembly | string | – | Reference genome assembly. Folklore currently accepts GRCh38 only. |
| query | string | yes | One germline nuclear SNV or simple indel to resolve and interpret; accepted forms include coordinates, genomic/coding/protein HGVS, SPDI, rsID, or a returned Folklore canonical_key in GRCh38:chrN:pos… |
| Name | Type | Req | Description |
|---|---|---|---|
| adapter_error | – | yes | – |
| contract_version | string | yes | – |
| record_url | string|null | yes | – |
| result | – | yes | – |
No examples provided.
get_gene_disease_associations Find diseases associated with a gene ~118
Find diseases associated with an exact gene symbol or HGNC identifier. Returns ClinGen gene-disease validity assertions, relation-specific inheritance, source reports and snapshot provenance, including conflicting and limited assertions.
| Name | Type | Req | Description |
|---|---|---|---|
| gene | string | yes | One public human gene symbol or HGNC identifier, for example BRCA1 or HGNC:1100. |
| limit | integer | – | Maximum number of source assertions per page, from 1 to 50. |
| offset | integer | – | Zero-based assertion offset; use the returned nextOffset when present. |
Structured output declared, but exposes no named fields.
No examples provided.
get_gene_profile Read the complete gene profile ~147
Read the selected gene_id and immutable snapshot_id from resolve_gene. Returns overview, disease validity, dosage, mechanisms, transcripts, native assemblies, constraint, ClinVar summaries and consequences, expression, GWAS, phenotypes and protein/pathways with source assertions, coverage, count units and null values. get_gene_section supplies further pages. Live search_gene_literature is separate from the snapshot literature section.
| Name | Type | Req | Description |
|---|---|---|---|
| gene_id | string | yes | Canonical HGNC gene_id returned by resolve_gene. Select an explicit candidate when resolution is ambiguous. |
| snapshot_id | string | yes | identity_snapshot_id returned by resolve_gene, or snapshot_id from the current gene profile. Restart resolution after snapshot_unavailable. |
| Name | Type | Req | Description |
|---|---|---|---|
| adapter_error | – | yes | – |
| contract_version | string | yes | – |
| record_url | string|null | yes | – |
| result | – | yes | – |
No examples provided.
get_gene_section Read a page of gene records ~192
Read a gene-profile section using gene_id, snapshot_id and its returned opaque cursor. Returns source records, assembly/release, coverage, totals, count units and provenance. snapshot_unavailable requires a fresh resolution/profile request.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | – | – | Opaque next_cursor returned for this same gene, snapshot and section. Omit for its first page. |
| gene_id | string | yes | Canonical HGNC gene_id returned by resolve_gene. Select an explicit candidate when resolution is ambiguous. |
| limit | integer | – | Maximum source records per page, from 1 to 50. Counts retain their original source unit. |
| section | string | yes | Source-qualified section from the current profile. Literature is a separate live capture; use search_gene_literature for it. |
| snapshot_id | string | yes | identity_snapshot_id returned by resolve_gene, or snapshot_id from the current gene profile. Restart resolution after snapshot_unavailable. |
| Name | Type | Req | Description |
|---|---|---|---|
| adapter_error | – | yes | – |
| contract_version | string | yes | – |
| record_url | string|null | yes | – |
| result | – | yes | – |
No examples provided.
get_publication_details Get details for a PubMed publication ~86
Retrieve one PMID from the PubMed-derived genetics corpus, including title, abstract, authors, journal, publication types, MeSH terms, gene and variant mentions, retraction status and PubMed/PMC links.
| Name | Type | Req | Description |
|---|---|---|---|
| pmid | string | yes | One PubMed identifier to look up in Folklore's current corpus, as 1 to 12 digits without a PMID prefix. |
Structured output declared, but exposes no named fields.
No examples provided.
resolve_gene Resolve a gene symbol, alias or stable identifier ~111
Resolve a human gene symbol, previous symbol, alias, HGNC, Ensembl or NCBI Gene identifier. Returns exact, alias, ambiguous, not_found or withdrawn status with candidates and identity_snapshot_id. Use a selected HGNC gene_id and snapshot_id with get_gene_profile. Gene-plus-HGVS and variant expressions use classify_germline_variant.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | One public gene symbol, previous symbol, alias, HGNC ID, Ensembl gene ID or NCBI Gene ID. |
| Name | Type | Req | Description |
|---|---|---|---|
| adapter_error | – | yes | – |
| contract_version | string | yes | – |
| record_url | string|null | yes | – |
| result | – | yes | – |
No examples provided.
search_disease_genes Find genes associated with a disease ~120
Find genes associated with an exact MONDO identifier or disease-name search. Returns ClinGen validity assertions with inheritance, source reports and snapshot provenance. Name searches can return multiple disease identities.
| Name | Type | Req | Description |
|---|---|---|---|
| disease | string | yes | One public disease name or exact MONDO identifier (MONDO: followed by seven digits). A name search may match multiple distinct diseases. |
| limit | integer | – | Maximum number of source assertions per page, from 1 to 50. |
| offset | integer | – | Zero-based assertion offset; use the returned nextOffset when present. |
Structured output declared, but exposes no named fields.
No examples provided.
search_gene_literature Find live literature for a resolved public gene ~183
Retrieve a live publication capture for a resolved gene_id and snapshot_id. Returns source links, match labels, capture time/hash, degradation and gene/snapshot/sort-bound cursors. This capture is separate from the immutable reference snapshot and contains no abstracts.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | – | – | Opaque next_cursor returned for this same gene, snapshot and sort. Omit for the first page. |
| gene_id | string | yes | Canonical HGNC gene_id returned by resolve_gene. Select an explicit candidate when resolution is ambiguous. |
| limit | integer | – | Maximum publication records in one live discovery page, from 1 to 25. |
| snapshot_id | string | yes | identity_snapshot_id returned by resolve_gene, or snapshot_id from the current gene profile. Restart resolution after snapshot_unavailable. |
| sort | string | – | Discovery ordering. Keep the same sort for continuation pages. |
| Name | Type | Req | Description |
|---|---|---|---|
| adapter_error | – | yes | – |
| contract_version | string | yes | – |
| record_url | string|null | yes | – |
| result | – | yes | – |
No examples provided.
search_literature_corpus Search the Folklore Literature Corpus ~171
Search the genetics Literature Corpus by question, PMID, DOI, PMCID, gene, variant, phenotype, HPO or OMIM concept. Known publication identifiers provide exact anchors. Returns ranked publications, match types, scores and source links.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | – | – | Opaque continuation cursor from the preceding response for the same query and sort order; omit for the first page. |
| limit | integer | – | Maximum number of publications to return, from 1 to 25. |
| query | string | yes | Natural-language literature question or exact PMID, DOI, PMCID, gene, variant, phenotype, HPO, or OMIM query. Include every known publication identifier when comparing or finding related papers. |
| sort | string | – | Result ordering: relevance-ranked, newest publication first, or oldest publication first. |
Structured output declared, but exposes no named fields.
No examples provided.
search_variant_literature Find literature for a germline variant ~183
Resolve one GRCh38 germline variant and retrieve publications from the PubMed-derived genetics corpus. Exact variant mentions rank ahead of broader gene associations. Returns match types, source links, corpus provenance and retrieval time.
| Name | Type | Req | Description |
|---|---|---|---|
| assembly | string | – | Reference genome assembly. Folklore currently accepts GRCh38 only. |
| limit | integer | – | Maximum number of publications to return, from 1 to 25. |
| query | string | yes | One germline nuclear SNV or simple indel to resolve before retrieving its literature; this is a variant identifier, not a natural-language question. Accepts a returned Folklore canonical_key in GRCh3… |
| question | – | – | Optional natural-language focus applied after the variant is resolved, such as a condition or evidence question; do not put the variant identifier here. |
Structured output declared, but exposes no named fields.
No examples provided.
support_helena Support Helena's free scientific infrastructure ~23
Retrieve Helena Good campaign, rules, manifest and MCP connection URLs.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the Folklore Clinical Variant Interpretation MCP server?
Folklore Clinical Variant Interpretation MCP is a hosted endpoint at https://api.helena.bio/folklore/v1/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 · api.helena.bio
claude mcp add --transport http helena-bioinformatics-folklore 'https://api.helena.bio/folklore/v1/mcp'
What is the Folklore Clinical Variant Interpretation MCP server?
Folklore Clinical Variant Interpretation MCP is listed in the public MCP registry as io.github.helena-bioinformatics/folklore. ACMG/AMP germline variant classification, gene profiles, disease associations and literature. This page covers its hosted endpoint (https://api.helena.bio/folklore/v1/mcp).
Is the Folklore Clinical Variant Interpretation MCP server safe to use?
Folklore Clinical Variant Interpretation MCP scores 81 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 Folklore Clinical Variant Interpretation MCP server expose?
Folklore Clinical Variant Interpretation MCP exposes 11 tools: classify_germline_variant, search_variant_literature, get_publication_details, search_literature_corpus, support_helena, and 6 more. Their descriptions and schemas cost roughly 1,509 tokens of context every time the server is loaded.
Does the Folklore Clinical Variant Interpretation MCP server require authentication?
No. We connected to Folklore Clinical Variant Interpretation MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Folklore Clinical Variant Interpretation MCP server still maintained?
Folklore Clinical Variant Interpretation MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.