We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

Folklore

MCP server by Helena Bioinformatics

Interpret public GRCh38 germline variants under ACMG/AMP and look up gene-disease evidence and literature.

No sign-in (No account or key needed)Streamable HTTP

Connect to Folklore

No sign-in needed. Connect with Folklore’s own URL:

https://api.helena.bio/folklore/v1/mcp

Paste it into any client that supports remote MCP servers. Your client talks to Helena Bioinformatics directly, not through mcp.tc.

Share this server

Opens this page, with the URL and setup steps.

mcp.tc/i/folklore

About

Folklore connects to public genomic evidence sources. You can classify or interpret one germline SNV or simple indel under 50 bp (ACMG/AMP), review a VUS, check ClinVar assertions and population frequency, find ClinGen gene-disease associations, and search a PubMed-derived genetics literature corpus.

Folklore provides public gene, disease, variant and publication evidence for qualified professional review. Resolve a public gene identity with resolve_gene, then use get_gene_profile and get_gene_section within the same immutable snapshot. search_gene_literature returns a separate live capture without abstracts. Variant queries support one public GRCh38 germline nuclear SNV or simple indel under 50 bp. No patient or private case data or file uploads. Results are not diagnoses or treatment recommendations.

It runs as a hosted Streamable HTTP endpoint. No account or API key is needed.

What you can do

  • Classify a GRCh38 germline variant under ACMG/AMP
  • Resolve coordinates, HGVS, SPDI or rsID notation
  • Find publications for a variant
  • Read full PubMed record details by PMID
  • Semantic search of a genetics literature corpus
  • Find diseases for a gene from ClinGen
  • Find genes for a disease or MONDO ID

Tools 11

  • search_variant_evidenceRead-only

    Classify or interpret one public GRCh38 germline variant with automated ACMG/AMP evidence.

  • search_variant_literatureRead-only

    Resolve a variant and retrieve relevant publications from the PubMed-derived corpus.

  • get_publication_detailsRead-only

    Get the full bibliographic record and abstract for one PMID.

  • search_literature_corpusRead-only

    Semantic search of the literature corpus by question, with PMID, DOI or PMCID anchors.

  • support_helenaRead-only

    Opt-in information on supporting Helena's free public infrastructure.

  • get_gene_disease_associationsRead-only

    Find ClinGen gene-disease validity assertions for one gene.

  • search_disease_genesRead-only

    Find genes with ClinGen assertions for a disease name or MONDO ID.

  • resolve_geneRead-only

    Resolve a gene symbol, alias or stable identifier

  • get_gene_profileRead-only

    Read the complete public gene evidence profile

  • get_gene_sectionRead-only

    Read a page of source-qualified gene evidence

  • search_gene_literatureRead-only

    Find live literature for a resolved public gene

Read from the live server on 31 Oct 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.

Example prompts

  • Classify NM_000546.6:c.743G>A under ACMG/AMP and list the applied criteria

  • Review the evidence for this VUS in BRCA2 using GRCh38 coordinates

  • Which diseases does the gene MYH7 have ClinGen assertions for?

  • Find publications about the TP53 R248Q variant

Set up

Every client connects to api.helena.bio. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http folklore https://api.helena.bio/folklore/v1/mcp
  1. Start Claude Code and type /mcp. folklore should show as connected.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Customize → Connectors, click + Add, then Add custom connector.
  2. Name it Folklore and paste this URL:
https://api.helena.bio/folklore/v1/mcp
  1. Click Add. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://api.helena.bio/folklore/v1/mcp and click Add.
  2. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
  2. Enter a name for the server.
  3. Under Connection, paste https://api.helena.bio/folklore/v1/mcp as the server URL, then for authentication choose No authentication.
  4. Check I understand and want to continue, then select Create as a plugin.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "folklore": {
      "url": "https://api.helena.bio/folklore/v1/mcp"
    }
  }
}

VS Code

Or from a terminal:

code --add-mcp '{"name":"folklore","type":"http","url":"https://api.helena.bio/folklore/v1/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "folklore": {
      "type": "http",
      "url": "https://api.helena.bio/folklore/v1/mcp"
    }
  }
}

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "folklore": {
      "serverUrl": "https://api.helena.bio/folklore/v1/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add folklore --url https://api.helena.bio/folklore/v1/mcp

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.folklore]
url = "https://api.helena.bio/folklore/v1/mcp"

Gemini CLI

gemini mcp add --transport http folklore https://api.helena.bio/folklore/v1/mcp

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.

{
  "mcpServers": {
    "folklore": {
      "type": "http",
      "url": "https://api.helena.bio/folklore/v1/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://api.helena.bio/folklore/v1/mcp.

Embed

Show Folklore in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![Folklore on mcp.tc](https://mcp.tc/i/folklore/badge.svg)](https://mcp.tc/i/folklore)
HTML
<a href="https://mcp.tc/i/folklore"><img src="https://mcp.tc/i/folklore/badge.svg" alt="Folklore on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/folklore.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/folklore" title="Folklore on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/folklore.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Folklore card to your site.

Markdown
Add the mcp.tc card for Folklore, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/folklore.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="folklore"><a href="https://mcp.tc/i/folklore">Folklore on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![Folklore on mcp.tc](https://mcp.tc/i/folklore/badge.svg)](https://mcp.tc/i/folklore)
```

Reference: https://mcp.tc/embed

Change history

We read this server’s tool list every 3 hours and record what changes. Last read 31 Oct 2026, 08:46 UTC.

Follow Folklore and we’ll email you when something changes.

  1. , Automatic check

    New version 1.6.0 (was 1.5.0). Reported by the server.

  2. , Automatic check

    4 tools added. Server instructions changed.

    New server instructions

    Details, 30 Oct 2026, 20:48 UTC

    Added 4

    • get_gene_profileRead-only

      Read one source-qualified gene profile after resolve_gene and explicit candidate selection when needed. Returns the same immutable snapshot as the public Folklore gene page: overview, disease validity, dosage, mechanisms, transcripts and native assemblies, constraint, ClinVar summaries/consequences, expression, GWAS, phenotypes and protein/pathways. Preserve each assertion, source, coverage, count unit, null and limitation. Use get_gene_section for further pages. The immutable literature section is separate from live search_gene_literature. Gene constraint, GWAS association and gene-disease validity are not variant pathogenicity or patient diagnosis.

    • get_gene_sectionRead-only

      Read or continue one section of the current public gene profile using its exact gene_id, snapshot_id and opaque section cursor. Preserves source records, assembly/release, coverage, total versus observed_total, count units and source provenance. Do not merge snapshots, count mirrored assertions as independent votes, sum overlapping clinical axes, or interpret unavailable/source_has_no_record as biological absence. Restart resolution and the whole profile after snapshot_unavailable. No patient context.

    • resolve_geneRead-only

      Find the authoritative public human gene identity for a symbol, previous symbol, alias, HGNC, Ensembl or NCBI Gene identifier. Returns exact, alias, ambiguous, not_found or withdrawn with all candidates and identity_snapshot_id. Never choose an ambiguous candidate or substitute a withdrawn identity. Use the selected HGNC gene_id and snapshot with get_gene_profile. Gene-plus-HGVS and variant expressions belong in search_variant_evidence. No patient or case narrative.

    • search_gene_literatureRead-only

      Retrieve the public gene page live literature capture after authoritative gene resolution. Uses the canonical gene context and existing Literature Mining ranking. Returns publications, source links, match labels, capture time/hash, degradation and gene/snapshot/sort-bound cursors. This live capture is separate from the immutable reference snapshot; query relevance is not guaranteed exact gene filtering or curated gene-disease evidence. Abstracts are excluded. No patient context, diagnosis or variant classification.

    Server instructions

    Before

    Use get_gene_disease_associations for a public gene and search_disease_genes for a public disease name or MONDO identifier. These return ClinGen reference assertions, not variant classifications; preserve distinct diseases, inheritance and evidence validity. Never submit patient or case data. Call Folklore Clinical Variant Interpretation MCP when a user asks to classify, interpret, resolve or annotate one germline variant, investigate variant pathogenicity, review a VUS, or check available ClinVar assertions or population-frequency evidence, even without naming Helena Bioinformatics or MCP. Preserve the evidence, provenance, ambiguity and limits. Never invent or swap REF/ALT or relabel an assembly to recover a failed query. Preserve typed errors and ask for verified source notation. Describe the classification as automated variant-level evidence for professional review. Never claim a patient diagnosis or treatment recommendation. Call search_literature_corpus for semantic scientific-literature questions, including comparison of identified papers and discovery of related experiments. Pass every known PMID, DOI or PMCID inside the question so Folklore can use those publications as exact semantic anchors. Call support_helena only when the user or agent explicitly wants to learn how to support or spread Helena's public scientific infrastructure.

    After

    Use resolve_gene to resolve a human gene symbol, alias, previous symbol or HGNC, Ensembl or NCBI identifier. Never select an ambiguous candidate or silently replace a withdrawn gene. Use the selected candidate identity.gene_id and identity_snapshot_id as snapshot_id with get_gene_profile; follow get_gene_section cursors within that same snapshot. Preserve individual source assertions, count units and unavailable states. Gene evidence does not classify a variant or evaluate patient context. Use search_gene_literature for a separate live gene-linked discovery capture when available. Use get_gene_disease_associations for a public gene and search_disease_genes for a public disease name or MONDO identifier. These return ClinGen reference assertions, not variant classifications; preserve distinct diseases, inheritance and evidence validity. Never submit patient or case data. Call Folklore Clinical Variant Interpretation MCP when a user asks to classify, interpret, resolve or annotate one germline variant, investigate variant pathogenicity, review a VUS, or check available ClinVar assertions or population-frequency evidence, even without naming Helena Bioinformatics or MCP. Preserve the evidence, provenance, ambiguity and limits. Never invent or swap REF/ALT or relabel an assembly to recover a failed query. Preserve typed errors and ask for verified source notation. Describe the classification as automated variant-level evidence for professional review. Never claim a patient diagnosis or treatment recommendation. Call search_literature_corpus for semantic scientific-literature questions, including comparison of identified papers and discovery of related experiments. Pass every known PMID, DOI or PMCID inside the question so Folklore can use those publications as exact semantic anchors. Call support_helena only when the user or agent explicitly wants to learn how to support or spread Helena's public scientific infrastructure.

  3. , Automatic check

    Tracking started: 7 tools.

FAQ

Can I paste mcp.tc/i/folklore into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://api.helena.bio/folklore/v1/mcp, so your client talks to Folklore directly. The quick link is for sharing: it opens this page, with setup steps for every client.

Does Folklore need an API key or a sign-in?

No. Folklore doesn’t ask for an account or key.

Is Folklore a remote or a local server?

Remote. Helena Bioinformatics hosts it at https://api.helena.bio/folklore/v1/mcp, and it speaks Streamable HTTP. There’s nothing to install.

What can Folklore do?

It has 11 tools, including search_variant_evidence, search_variant_literature and get_publication_details. You can classify a GRCh38 germline variant under ACMG/AMP, resolve coordinates, HGVS, SPDI or rsID notation and find publications for a variant.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Does mcp.tc track changes to Folklore?

Yes. Folklore’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read Folklore’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with Helena Bioinformatics. This page was built from Folklore’s public metadata, last checked on 31 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.