| name | pathway-report |
| description | Generate a pathway deep-dive report combining Reactome pathway data, member gene summaries, ClinVar variants, and PubMed literature |
Generate a comprehensive pathway deep-dive report for: $ARGUMENTS
Use the MCP tools available to you to gather data from all relevant sources, then synthesize a single structured report. Follow the steps below in order. If a step fails or returns no data, note the gap and continue — do not stop the report.
Data Gathering Steps
1. Pathway Identification
- If the input looks like a Reactome stable ID (starts with
R-), call reactome_get_pathway with pathway_id set to that ID, with include_participants: true and include_hierarchy: true.
- Otherwise, call
reactome_get_pathway with query set to the input to search for matching pathways. Present the top hits and pick the most relevant one, then do a direct lookup with include_participants: true and include_hierarchy: true.
2. Pathway Overview
From the Reactome data, extract:
- Pathway name, stable ID, and species
- Summation/description
- Position in the pathway hierarchy (parent pathways)
- Sub-events (child pathways and reactions) — list the first 10-15
- Compartments (cellular locations)
- Whether it is disease-associated
3. Key Member Genes
- From the participants list, identify the gene/protein participants (filter for UniProt/ReferenceGeneProduct entries).
- Select up to 10 key genes from the participant list.
- Call
batch_gene_summary with those gene symbols (taxon: human) to get brief summaries.
- For the top 3-5 most important genes, call to get function descriptions and GO terms.
