loading…
Search for a command to run...
loading…
Provides access to AlphaFold predicted protein 3D structures from EBI, enabling retrieval of prediction metadata, summaries, annotations, and UniProt data.
Provides access to AlphaFold predicted protein 3D structures from EBI, enabling retrieval of prediction metadata, summaries, annotations, and UniProt data.
AlphaFold DB MCP — predicted protein structures.
Part of Pipeworx — an MCP gateway connecting AI agents to 965+ live data sources.
| Tool | Description |
|---|---|
prediction |
Full prediction metadata + structure file URLs (PDB, CIF, PAE). |
summary |
Short summary for a prediction (organism, sequence, mean pLDDT). |
annotations |
Sequence-level annotations (e.g. MUTAGEN, LOW_CONFIDENCE_REGIONS). |
uniprot |
Fetch AlphaFold structure prediction metadata (PDB/CIF/PAE download URLs, pLDDT scores) by UniProt accession (e.g. "P00533"); equivalent to prediction but takes uniprot_id explicitly. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"alphafold": {
"url": "https://gateway.pipeworx.io/alphafold/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 965+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Alphafold data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
Выполни в терминале:
claude mcp add mcp-alphafold -- npx Да, Alphafold MCP бесплатный — установка в один клик через Unyly без оплаты.
Нет, Alphafold работает без API-ключей и переменных окружения.
Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.
Открой Alphafold на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
CSA PROJECT - FZCO © 2026 IFZA Business Park, DDP, Premises Number 31174 - 001
Безопасность
Низкий рискАвтоматическая эвристика по публичным данным — не гарантия безопасности.