UniProt MCP Server
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_proteinsC | Search UniProt database for proteins by name, keyword, or organism |
| get_protein_infoC | Get detailed information for a specific protein by UniProt accession |
| search_by_geneC | Search for proteins by gene name or symbol |
| get_protein_sequenceC | Get the amino acid sequence for a protein |
| get_protein_featuresC | Get functional features and domains for a protein |
| compare_proteinsB | Compare multiple proteins side-by-side with sequence and feature comparison |
| get_protein_homologsC | Find homologous proteins across different species |
| get_protein_orthologsC | Identify orthologous proteins for evolutionary studies |
| get_phylogenetic_infoC | Retrieve evolutionary relationships and phylogenetic data |
| get_protein_structureC | Retrieve 3D structure information from PDB references |
| get_protein_domains_detailedC | Enhanced domain analysis with InterPro, Pfam, and SMART annotations |
| get_protein_variantsC | Disease-associated variants and mutations |
| analyze_sequence_compositionC | Amino acid composition, hydrophobicity, and other sequence properties |
| get_protein_pathwaysC | Associated biological pathways (KEGG, Reactome) |
| get_protein_interactionsD | Protein-protein interaction networks |
| search_by_functionC | Search proteins by GO terms or functional annotations |
| search_by_localizationB | Find proteins by subcellular localization |
| batch_protein_lookupC | Process multiple accessions efficiently |
| advanced_searchC | Complex queries with multiple filters (length, mass, organism, function) |
| search_by_taxonomyC | Search by detailed taxonomic classification |
| get_external_referencesD | Links to other databases (PDB, EMBL, RefSeq, etc.) |
| get_literature_referencesC | Associated publications and citations |
| get_annotation_confidenceD | Quality scores for different annotations |
| export_protein_dataC | Export data in specialized formats (GFF, GenBank, etc.) |
| validate_accessionC | Check if accession numbers are valid |
| get_taxonomy_infoC | Detailed taxonomic information for organisms |
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 26 tools
Most tools have distinct purposes targeting specific UniProt data aspects, but some overlap exists. For example, 'get_protein_info' and 'get_protein_sequence' could be confused as both retrieve protein data, though their descriptions clarify the distinction. Overall, the set is well-organized with clear boundaries for most tools.
Tool names follow a highly consistent verb_noun pattern throughout, such as 'get_protein_info', 'search_by_function', and 'analyze_sequence_composition'. This predictability makes it easy for agents to understand and select tools without confusion, enhancing usability.
With 26 tools, the count is borderline high for a single server, potentially overwhelming for agents. While UniProt is a complex domain, this many tools might indicate over-specialization or fragmentation, making it harder to navigate efficiently.
The tool set provides comprehensive coverage for UniProt data access, including search, retrieval, analysis, and export functions. It covers all major aspects like sequences, structures, interactions, and annotations, with no obvious gaps for typical agent workflows in this domain.