gget_alphafold
Predict protein structure using AlphaFold and save to local file.
LABSCO SUMMARY
A genomics bench that assumes lookups will be chained, and says so in the tools themselves.
The ordering constraint is written into the descriptions — search first for Ensembl IDs, then info, seq, bgee and opentargets take them — which is the difference between an agent that carries the right identifier forward and one that guesses at a symbol. The width has a price: some tools answer only after gget_setup has installed their dependencies, and the heaviest query in the set comes with a hardware footnote rather than a spinner.
What it is
An MCP surface over the gget bioinformatics toolkit, 20 tools spanning gene search, sequence retrieval, alignment, structure prediction and public expression databases.
What you get
- Gene symbols resolved to Ensembl IDs in batches, which the metadata, sequence and association tools then require
- Gene and transcript metadata for those IDs, and sequences written to a local file, optionally translated
- Reference genome and annotation FTP links by species
- Similarity search and alignment: BLAST against a BLAST database, BLAT against a UCSC assembly, MUSCLE and DIAMOND alignments saved to file
- Expression and association data from ARCHS4, Bgee, OpenTargets and CZ CELLxGENE Census, plus functional enrichment through Enrichr
- Structures fetched from PDB or predicted with AlphaFold, and linear motifs predicted locally from a sequence or UniProt ID
- COSMIC cancer-mutation search, and sequences mutated according to standard annotation
Requirements
No key. Third-party dependencies for the modules you intend to use, which gget_setup installs per module, and a writable output_path for the tools that save sequences, alignments and structures. gget_cellxgene's own note puts large Census queries above 16 GB of RAM and a 5 Mbps connection.
Setup effort
One command — uvx gget-mcp stdio
USE CASES
01
Going from a gene symbol in a paper to its actual record
Resolve the symbols to Ensembl IDs first — several at once — then pull metadata for them and write the sequences to a file, translated if you want protein.
02
Placing a sequence you have against what is already known
Search it against a BLAST database or a UCSC assembly depending on what you are looking for, then align the hits with MUSCLE, or use DIAMOND when the set is large enough that speed decides.
03
Asking what a gene is associated with clinically
With the Ensembl ID in hand, pull the diseases and drugs linked to it, the expression and orthologs recorded for it, and the tissue atlas or correlated genes that put it in context.
04
Making sense of a gene list that came out of an experiment
Run functional enrichment over the list through Enrichr, and query single-cell data to see which cell types and tissues the interesting members actually appear in.
05
Getting a structure to work from
Fetch the deposited structure when one exists, predict it with AlphaFold when it does not, and check the sequence for linear motifs that a fold view will not show you.
06
Working with a cancer mutation someone reported
Look the mutation up in COSMIC, then apply it to the reference sequence in standard annotation so you have the mutated sequence to hand rather than a description of one.
20 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
gget_archs4
Find correlated genes or tissue expression atlas using ARCHS4 RNA-seq database.
gget_bgee
Get orthologs or expression data for a gene from Bgee database.
PREREQUISITE: Use search_genes to get Ensembl ID first.
gget_blast
BLAST a nucleotide or amino acid sequence against any BLAST database.
gget_blat
BLAT a nucleotide or amino acid sequence against any BLAT UCSC assembly.
gget_cellxgene
Query single-cell RNA-seq data from CZ CELLxGENE Discover using Census.
NOTE: Querying large datasets requires >16 GB RAM and >5 Mbps internet connection.
gget_cosmic
Search COSMIC database for cancer mutations or download COSMIC databases.
gget_diamond
Align sequences using DIAMOND and save to local file.
gget_elm
Locally predict Eukaryotic Linear Motifs from amino acid sequence or UniProt ID.
gget_enrichr
Perform functional enrichment analysis on gene list using Enrichr.
gget_info
Get detailed gene and transcript metadata using Ensembl IDs.
PREREQUISITE: Use search_genes first to get Ensembl IDs from gene names/symbols.
gget_muscle
Align sequences using MUSCLE and save to local file.
gget_mutate
Mutate nucleotide sequences according to provided mutations in standard annotation.
gget_opentargets
Query OpenTargets for diseases, drugs, and other data associated with a gene.
PREREQUISITE: Use search_genes to get Ensembl ID first.
gget_pdb
Fetch PDB structure and save to local file in stdio mode.
gget_ref
Fetch FTPs for reference genomes and annotations by species from Ensembl.
gget_search
General search for any biological terms using gene symbols, names, or synonyms.
This is a general search that looks broadly across gene names and descriptions. For specific gene symbol searches, use search_genes_simple instead.
gget_search_genes
Search for specific genes using gene symbols with enhanced search strategy.
🚀 BATCH PROCESSING SUPPORTED: This function can process multiple genes in a single call! Use this tool FIRST when you have gene names/symbols and need to find their Ensembl IDs. Returns Ensembl IDs which are required for get_gene_info and get_sequences tools.
IMPORTANT: Due to limitations in Ensembl search, short gene names often fail to find results. For best results, provide descriptive terms along with gene symbols:
RECOMMENDED FORMAT: "GENE_SYMBOL descriptive_terms" Examples:
- Instead of: "APP"
- Use: "APP amyloid precursor" or "APP amyloid beta precursor protein"
- Instead of: ["BACE1", "MAPT"]
- Use: ["BACE1 beta secretase", "MAPT microtubule tau"]
This function uses AND search for multi-word terms and OR search for single words.
Args: search_terms: SINGLE gene symbol OR LIST of gene symbols with descriptive terms Single: 'APP amyloid precursor' Batch: ['BACE1 beta secretase', 'MAPT tau', 'APOE apolipoprotein'] species: Target species (e.g., 'homo_sapiens', 'mus_musculus') id_type: "gene" (default) or "transcript" - whether to return genes or transcripts
Returns: SearchResult: DataFrame with gene search results containing Ensembl IDs and descriptions Results from ALL search terms are combined in a single response
Example (SINGLE GENE): Input: search_terms='APP amyloid precursor', species='homo_sapiens' Output: DataFrame with APP gene and related genes
Example (BATCH PROCESSING, limit number of queries to 3-5 to avoid timeouts): Input: search_terms=['APOE apolipoprotein', 'APP amyloid', 'PSEN1 presenilin'], species='homo_sapiens' Output: DataFrame with ALL three genes and their Ensembl IDs in one response
Downstream tools that need the Ensembl IDs from this search:
- get_gene_info: Get detailed gene information
- get_sequences: Get DNA/protein sequences
Note: For general biological term searches without gene focus, use search_simple.
gget_seq
Fetch sequences and save to local file in stdio mode.
PREREQUISITE: Use search_genes first to get Ensembl IDs from gene names/symbols.
gget_setup
Install third-party dependencies for specified gget modules.
BEFORE YOU INSTALL
What to know first
Tools you get
20 tools when we connected. The documentation lists 13; gget_bgee, gget_diamond, gget_elm, gget_mutate, gget_opentargets, gget_search_genes and gget_setup are available but undocumented.
Requires
uvx on PATH
Where it runs
All 4 documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 20 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx gget-mcp stdioMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"gget": {
"command": "uvx",
"args": [
"--from",
"gget-mcp@latest",
"stdio"
]
}
}
}Cursor, Windsurf
JSON
{
"mcpServers": {
"gget-mcp": {
"command": "uvx",
"args": [
"--from",
"gget-mcp@latest",
"stdio"
]
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"gget-mcp": {
"command": "uvx",
"args": [
"--from",
"gget-mcp@latest",
"stdio"
]
}
}
}
