Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AGR MCP Server search for TP53 gene in human and show disease associations"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for querying Alliance of Genome Resources - genomics data across model organisms.
No installation required. Add to your MCP client config:
{
"mcpServers": {
"agr-genomics": {
"command": "npx",
"args": ["-y", "agr-mcp-server"]
}
}
}npm install -g agr-mcp-serverThen use in your config:
{
"mcpServers": {
"agr-genomics": {
"command": "agr-mcp-server"
}
}
}Client | Config path |
Claude Desktop (macOS) |
|
Claude Desktop (Windows) |
|
Claude Code |
|
Cursor | Settings > MCP Servers |
Windsurf |
|
Related MCP server: gwas-mcp
Ask questions naturally:
"Search for BRCA1 genes in human"
"What genes are involved in DNA repair?"
"Get information about HGNC:1100"
"Find orthologs of insulin gene"
"What diseases are associated with TP53?"
"Show me expression data for daf-2 in worm"
"Find all human genes with kinase activity"
"Query AllianceMine for mouse genes on chromosome 11"
Human, mouse, rat, zebrafish, fly, worm, yeast, xenopus
Tool | Description |
| Search genes with optional species filter |
| Detailed gene information (symbol, location, synonyms) |
| Disease associations for a gene |
| Search diseases by name |
| Expression data across tissues/stages |
| Cross-species homologs |
| Phenotype annotations |
| Molecular and genetic interactions |
| Alleles/variants for a gene |
| Search alleles by name |
| List supported model organisms |
Tool | Description |
| Search AllianceMine for genes, proteins, diseases |
| Run raw PathQuery XML queries |
| Build queries using JSON DSL |
| Natural language query (returns schema for LLM) |
| List available query templates |
| Run a pre-built query template |
| Get available gene/protein lists |
| Get contents of a specific list |
| Create a new list (requires auth) |
| Add items to a list (requires auth) |
| Delete a list (requires auth) |
Using query builder:
Find human genes with BRCA in symbol:
- from: Gene
- select: primaryIdentifier, symbol, name
- where: organism.shortName = "H. sapiens", symbol CONTAINS "BRCA"Using templates:
Gene_Alleles - Find alleles for a gene
Gene_DOTerm - Disease annotations for a gene
Gene_GOTerms - GO annotations for a gene
GOTerm_Genes - Find genes by GO termList management operations (mine_create_list, mine_add_to_list, mine_delete_list) require an AllianceMine API token:
{
"mcpServers": {
"agr-genomics": {
"command": "npx",
"args": ["-y", "agr-mcp-server"],
"env": {
"ALLIANCEMINE_TOKEN": "your-token-here"
}
}
}
}Species | Format | Example |
Human |
|
|
Mouse |
|
|
Rat |
|
|
Zebrafish |
|
|
Fly |
|
|
Worm |
|
|
Yeast |
|
|
Xenopus |
|
|
MIT
Find orthologous genes across species. Returns homologs from all Alliance model organisms.
Inputs: gene_id (required).
Get alleles/variants associated with a gene.
Inputs: gene_id (required), limit.
Get disease associations for a gene, including human disease models and annotations.
Inputs: gene_id (required), limit.
Get expression data for a gene including tissue/cell type expression and developmental stages.
Inputs: gene_id (required), limit.
Get detailed information about a specific gene including symbol, name, location, species, and cross-references.
Inputs: gene_id (required).
Get molecular and genetic interactions for a gene.
Inputs: gene_id (required), limit.
Get phenotype annotations for a gene.
Inputs: gene_id (required), limit.
Get list of model organisms supported by Alliance of Genome Resources.
Inputs: no named parameters.
Add items to an existing list. Requires ALLIANCEMINE_TOKEN environment variable.
Inputs: name (required), identifiers (required).
Create a new list in AllianceMine. Requires ALLIANCEMINE_TOKEN environment variable.
Inputs: name (required), type (required), identifiers (required), description.
Delete a list from AllianceMine. Requires ALLIANCEMINE_TOKEN environment variable.
Inputs: name (required).
Get the contents of a specific list.
Inputs: name (required).
Get all available gene/protein lists in AllianceMine.
Inputs: type.
List available query templates in AllianceMine. Templates are pre-built queries for common use cases.
Inputs: no named parameters.
Process a natural language query and return schema information to construct a structured AllianceMine query.
This tool returns the AllianceMine schema so you can convert the user's natural language into a mine_query_builder call.
Inputs: query (required), limit.
Run a raw PathQuery XML query against AllianceMine. For power users who know InterMine PathQuery syntax.
Inputs: xml (required).
Build and run structured queries against AllianceMine using a JSON DSL.
Example query - find human genes in DNA repair pathway: { "from": "Gene", "select": ["symbol", "name", "organism.name", "pathways.name"], "where": { "organism.name": "Homo sapiens", "pathways.name": { "op": "CONTAINS", "value": "DNA repair" } }, "limit": 50 }
Supported operators: =, !=, CONTAINS, LIKE, <, >, <=, >=, ONE OF, NONE OF, IS NULL, IS NOT NULL
Inputs: from (required), select (required), where, joins, +2 more.
Run a pre-built query template with parameters.
Parameter format: Use numeric keys ("1", "2", etc.) matching constraint positions.
Simple: {"1": "BRCA1"} - just the value
Full: {"1": {"path": "Gene", "op": "LOOKUP", "value": "BRCA1"}}
Common templates:
Gene_Orthologs: Find orthologs (params: {"1": {"path": "Gene", "op": "LOOKUP", "value": "HGNC:1100"}})
Gene_GOTerms: GO annotations for a gene
Gene_DOTerm: Disease annotations for a gene
GOTerm_Genes: Find genes by GO term
Use mine_list_templates to discover all available templates and their constraints.
Inputs: name (required), params (required), limit.
Search AllianceMine for genes, proteins, diseases, and other biological entities using keyword search.
Inputs: query (required), type, limit.
Search for alleles/variants in the Alliance database.
Inputs: query (required), limit.
Search for diseases in the Alliance database.
Inputs: query (required), limit.
Search for genes across all Alliance of Genome Resources model organisms. Supports species filtering.
Inputs: query (required), species, limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 22 tools
Most tools have distinct purposes, but there is some overlap between search_genes and find_orthologs (both involve gene-related queries across species), and between mine_query, mine_query_builder, and mine_natural_query (all for querying AllianceMine, though they differ in input format). The descriptions help clarify these distinctions, but an agent might occasionally misselect between them.
The naming is mostly consistent with a verb_noun pattern (e.g., get_gene_info, search_genes, mine_create_list), but there are minor deviations like mine_natural_query (which uses 'natural' as an adjective) and the mix of 'get' vs. 'search' prefixes for similar actions. Overall, the pattern is predictable and readable.
With 22 tools, the count feels borderline heavy for a genomics server, though it covers both gene data retrieval and AllianceMine operations. It might overwhelm agents with too many options, but the scope is broad enough to justify a larger set, making it reasonable but not ideal.
The tool set provides comprehensive coverage for the domain of genomic data and AllianceMine interactions. It includes CRUD operations for lists (create, get, delete, add), extensive gene data retrieval (info, expression, diseases, etc.), and multiple query methods (search, templates, natural language, structured), leaving no obvious gaps for agent workflows.
Knowledge graph ingestion, entity search, ontology analysis, and CoPass scoring.
Find pharmacogenomics guidelines, translate diplotypes, and retrieve prescribing recommendations.
Monarch Initiative MCP — biomedical knowledge graph.
Linked life-science search: 43M+ papers, 1.2M+ trials, drugs, genes, FDA/EMA approvals, patents.
