UniProt MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HTTP_HOST | No | HTTP server bind address | 0.0.0.0 |
| MCP_HTTP_PORT | No | HTTP server port | 8000 |
| MCP_HTTP_RELOAD | No | Enable auto-reload: 1 or true | 0 |
| UNIPROT_LOG_LEVEL | No | Logging level: debug, info, warning, error | info |
| MCP_HTTP_LOG_LEVEL | No | Uvicorn log level | info |
| UNIPROT_LOG_FORMAT | No | Log format: plain or json | plain |
| UNIPROT_ENABLE_FIELDS | No | Request minimal field subsets to reduce payload size | |
| MCP_CORS_ALLOW_HEADERS | No | CORS allowed headers | * |
| MCP_CORS_ALLOW_METHODS | No | CORS allowed methods | GET,POST,DELETE |
| MCP_CORS_ALLOW_ORIGINS | No | CORS allowed origins (comma-separated) | * |
| UNIPROT_MAX_CONCURRENCY | No | Max concurrent UniProt API requests | 8 |
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 |
|---|---|
| fetch_entryC | Return a structured UniProt entry. |
| get_sequenceA | Return only the sequence metadata for an accession. |
| search_uniprotC | Search UniProtKB and return curated hits. |
| fetch_entry_flatfileC | Return the UniProt flatfile (txt or fasta) for a specific entry version. |
| map_idsC | Map identifiers between UniProt-supported namespaces. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| summarize_protein | Generate instructions for summarising a UniProt entry. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| search_help | Static help text explaining search conventions. |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: fetch_entry retrieves structured data, fetch_entry_flatfile provides flatfile formats, get_sequence focuses on sequence metadata, map_ids handles identifier mapping, and search_uniprot performs searches. There is no overlap or ambiguity between these functions.
The naming is mostly consistent with a verb_noun pattern (e.g., fetch_entry, get_sequence, map_ids, search_uniprot), but fetch_entry_flatfile deviates slightly by including an extra descriptor. Overall, the pattern is readable and predictable.
With 5 tools, this server is well-scoped for the UniProt domain. Each tool serves a specific, essential function without redundancy, making the count appropriate for typical use cases like data retrieval, mapping, and searching.
The toolset covers core operations for UniProt access: fetching entries in different formats, getting sequences, mapping IDs, and searching. A minor gap might be the lack of update or delete tools, but these are likely unnecessary for a read-only biological database, so agents can work effectively with the provided tools.