| name | variant-report |
| description | Generate a variant annotation report combining Ensembl, ClinVar, and UniProt data for a gene or genomic region |
Generate a comprehensive variant annotation report for: $ARGUMENTS
Use the MCP tools available to you to gather variant data from all relevant sources, then synthesize a single structured report. Follow the steps below. If a step fails, note the gap and continue.
Determine Input Type
First, classify the input:
- Gene symbol (e.g., TP53, BRCA1): Look up genomic coordinates first, then find variants in that region.
- Genomic region (e.g., 7:140453136-140453236): Use directly for variant lookup.
- Specific variant (e.g., NM_007294.4:c.5266dupC or rs ID): Search ClinVar directly.
Data Gathering Steps
For Gene Symbol Input:
1. Gene Coordinates
- Call
ensembl_lookup_gene with the gene symbol to get chromosomal coordinates.
- Note the chr:start-end for variant queries.
2. Known Variants in the Region
- Call
ensembl_get_variants with the gene's region (species: homo_sapiens, limit: 100).
- Summarize: total variants found, breakdown by consequence type, any with clinical significance.
3. ClinVar Annotations
- Call
clinvar_search with the gene symbol (limit: 20) to get clinical interpretations.
- Call
clinvar_search with "[gene] AND pathogenic" to specifically find pathogenic variants.
- Summarize: total entries, breakdown by clinical significance (pathogenic, likely pathogenic, VUS, benign).
4. Protein Feature Context
- Call
uniprot_search with the gene symbol and organism_id:9606 (reviewed: true) to find the UniProt accession.
