A side-by-side look at the Uniprot and MCP Server Neon MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Uniprot for databases work as a local process; choose MCP Server Neon for databases as a local process. You can also run both side by side in one mcpServers block.
search, get, proteomes_search.NEON_API_KEY.projects, branches, endpoints.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Databases | Databases |
| Quality signal | 57/100 · Good | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | OAuth 2.0 |
| Pricing | Not declared | Freemium |
| Required env vars | None listed | NEON_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 654 |
| Directory activity | 1 views 0 installs 0 upvotes | 5 views 0 installs 0 upvotes |
| Tools | 6 | 80 |
| Full listing | View Uniprot | View MCP Server Neon |
search"Find protein [name]" / "look up [gene] in UniProt" / "BRCA1 / TP53 / insulin protein info" / "all proteins for [organism]" — UniProtKB search via Lucene-style queries (e.g. gene:BRCA1 AND organism_id:9606 for human BRCA1). UniProt is the authoritative protein-sequence-and-function database — use for protein characterization, function annotation, sequence retrieval, and cross-references to PDB/GO/PubMed.get"Fetch protein [P12345]" / "UniProt entry for [accession]" / "FASTA sequence for [protein]" — single UniProtKB entry by accession (e.g. P12345 or P38398 for BRCA1_HUMAN). Returns full protein record: sequence, function annotations, GO terms, cross-refs, post-translational modifications, variants. Pass format=fasta for sequence only.proteomes_search"Reference proteome for [organism]" / "complete protein set of [species]" — search UniProt reference proteomes (the curated representative protein set per organism). Use as a starting point for genome-scale protein analyses.taxonomy_search"NCBI taxonomy ID for [organism]" / "taxid for [species]" / "look up [Latin name] in NCBI taxonomy" — search NCBI Taxonomy via UniProt's mirror. Returns taxonomic IDs you can use as organism_id filters in `search` (9606 = human, 10090 = mouse, 7227 = D. melanogaster, etc).keyword"UniProt keyword KW-N info" / "what does keyword [X] mean" — fetch a UniProt controlled-vocabulary keyword by ID. Use to look up annotation tags like "Kinase" / "Membrane" / "Disease-associated".feature_summary"Domain map of [protein]" / "annotated features of [accession]" / "what regions / sites does [protein] have" — annotated features (domains, active sites, transmembrane regions, mutagenesis sites, glycosylation, disulfide bonds, etc.) for a UniProt accession. Use for structural/functional analysis without pulling the full protein record.projectsbranchesendpointssnapshotsschemaqueryingneon_authdata_apiobservabilitydocsfunctionsstoragePaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"uniprot": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-uniprot"
]
}
}
}
{
"mcpServers": {
"neondatabase-mcp-server-neon": {
"command": "npx",
"args": [
"-y",
"neon@latest"
],
"env": {
"NEON_API_KEY": "YOUR_NEON_API_KEY_HERE"
}
}
}
}