Folklore Variant Evidence
Resolve one supported GRCh38 germline variant and return structured, source-backed ACMG/AMP evidence with provenance and explicit limitations. The public server is read-only and intended for professional review.
README
Folklore
Folklore is a public, read-only MCP server from Helena Bioinformatics. Its current Variant Evidence capability resolves one supported GRCh38 germline variant and returns structured evidence for ACMG/AMP classification.
The service accepts genomic, coding, and protein HGVS expressions. It normalizes the query to GRCh38 and returns the resolved variant, gene and consequence, automated classification, applied evidence codes, ClinVar assertions, population frequency, in-silico and splice predictions, source versions, provenance, limitations, and a link to the public Folklore Variant Details record.
Connect
- Endpoint:
https://api.helena.bio/folklore/v1/mcp - Transport: Streamable HTTP
- Authentication: None
- Tool:
search_variant_evidence
Example client configuration:
{
"mcpServers": {
"folklore": {
"url": "https://api.helena.bio/folklore/v1/mcp"
}
}
}
Registry build
The Dockerfile in this repository is a small distribution bridge used by
registries that build and inspect MCP servers from source. It runs a pinned
version of mcp-proxy and connects
its standard-input transport to the public Folklore Streamable HTTP endpoint.
The bridge contains no Folklore backend implementation, private data, secrets, or patient information. Clients that support Streamable HTTP should use the public endpoint above directly.
Query
Send one supported germline variant. For example:
ENST00000226413.5:c.317A>G
The same variant may be submitted as a supported genomic or protein HGVS expression.
Response
The tool returns structured, source-backed data suitable for machine use and a rendered Variant Details view for compatible chat clients. Results may include:
- input resolution status and warnings;
- GRCh38 genomic, coding, and protein HGVS;
- gene, transcript, consequence, exon, and identifiers;
- automated ACMG/AMP classification and evidence codes;
- ClinVar significance, review status, and associated conditions;
- gnomAD population frequency;
- in-silico, splice, conservation, and gene-constraint evidence;
- classifier and source-data versions;
- provenance, limitations, and a public Folklore record URL.
Scope and safety
Folklore provides computational decision support, not a diagnosis. Results must be reviewed by a qualified genetics professional in the relevant clinical context.
The public service accepts one variant query at a time. It does not accept patient records, expose private Helena Bioinformatics systems, or publish backend source code or implementation details.
Official links
Contact
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.