mcp-server-bioscience
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_literatureA | Search PubMed for biomedical literature and fetch abstracts. Useful for finding the latest research on diseases, drugs, or genes. Args: query: Search keywords (e.g., "KRAS lung cancer"). max_results: Maximum number of papers to return. |
| get_protein_structureA | Fetch AlphaFold 3D protein structure metadata and pLDDT confidence scores. Args: uniprot_id: The UniProt accession ID (e.g., "P00533" for EGFR). |
| get_gene_infoA | Look up gene details and genomic coordinates from Ensembl. Args: gene_symbol: The gene name (e.g., "BRCA1"). species: The species name (default: "human"). |
| get_chembl_moleculeA | Search the ChEMBL database for molecules and drugs by name or SMILES. Args: query: The compound name (e.g., "aspirin") or ID. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a distinct bioscience database: PubMed for literature, AlphaFold for protein structure, Ensembl for gene info, and ChEMBL for molecules. There is no overlap in purpose or resource.
All tool names follow a consistent verb_noun pattern: search_literature, get_protein_structure, get_gene_info, get_chembl_molecule. The verbs 'search' and 'get' are used predictably based on the action performed.
With just 4 tools, the server is carefully scoped to cover the most common bioscience queries. This is within the ideal range and each tool earns its place.
The set covers literature search, gene lookup, protein structure, and molecule search, providing a solid foundation for bioscience research. Missing features like variant or pathway lookup are minor gaps rather than critical dead ends.