ENCODE Toolkit
Search ENCODE, cross-reference 14 genomics databases, run analysis pipelines, and generate publication-ready methods from natural language.
Add to your client
Copy the config for your MCP client and paste it into its config file.
claude mcp add encode -- uvx encode-toolkitPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"encode-toolkit": {
"command": "uvx",
"args": [
"encode-toolkit"
]
}
}
}Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.
Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf
Before you start
- uvx (from uv) or Node.js/npx, or pip — to run the encode-toolkit package
- An MCP-compatible client (Claude Code, Claude Desktop, Cursor, Windsurf, or VS Code)
- Optional: ENCODE account access keys for restricted/unreleased data
About ENCODE Toolkit
An MCP server (and Claude Code plugin) for the ENCODE Project that lets you search, download, track, and analyze functional-genomics experiments from natural language. It provides 20 live-API tools covering search/discovery, file listing and batch download, local experiment tracking, citation export, experiment comparison, provenance logging, and cross-server reference linking. The plugin distribution additionally bundles 47 workflow skills and 7 Nextflow pipelines, but the MCP server installs standalone with uvx, npx, or pip.
Tools & capabilities (20)
encode_search_experimentsSearch ENCODE experiments with 20+ filters (assay title, organism, organ, biosample type, target, biosample term name, limit).
encode_get_experimentGet full details for a single experiment by accession, including all files, quality metrics, and audit info.
encode_download_filesDownload specific files by accession to a local directory, with organization options and optional MD5 verification.
encode_batch_downloadSearch and download in one step; runs in preview (dry_run) mode by default until disabled.
encode_track_experimentTrack an experiment locally along with its publications, methods, and pipeline info.
encode_list_filesList files for a specific experiment with format, output type, assembly, and preferred-default filters.
encode_search_filesSearch files across all experiments combining experiment-level and file-level filters.
encode_get_metadataList valid filter values for any parameter (assays, organisms, organs, biosample types, file formats, output types, assemblies).
encode_get_facetsGet live counts from ENCODE showing what data exists for given filters.
encode_get_file_infoGet detailed metadata for a single file by accession.
encode_manage_credentialsStore, check, or clear ENCODE credentials for restricted data access (stored encrypted in the OS keyring).
encode_list_trackedList all locally tracked experiments with metadata, publication counts, and derived file counts.
encode_get_citationsGet publications for tracked experiments and export them as JSON, BibTeX, or RIS.
encode_compare_experimentsAnalyze whether two experiments are compatible for combined analysis.
encode_summarize_collectionGet grouped statistics of your tracked experiment collection.
encode_log_derived_fileLog a file you created from ENCODE data (source accessions, tool, parameters) for provenance tracking.
encode_get_provenanceView provenance chains from derived files back to source ENCODE data.
encode_export_dataExport tracked experiments as a table in CSV, TSV, or JSON for Excel, R, or pandas.
encode_link_referenceLink external references (PubMed, bioRxiv, ClinicalTrials, GEO, DOI) to tracked experiments.
encode_get_referencesGet external references linked to tracked experiments for cross-server workflows.
What this server can do
ENCODE Toolkit provides tools for these capabilities — tap one to see every MCP server that does the same:
When to use it
- Find functional-genomics experiments (e.g. histone ChIP-seq for human pancreas) and return a structured table of targets, replicates, and file counts.
- Batch-download FASTQ/BAM/BED/bigWig files from ENCODE organized by experiment with MD5 verification.
- Track experiments with their publications and export citations as BibTeX or RIS for a manuscript.
- Log derived files and view provenance chains from source ENCODE accessions to processed outputs.
- Cross-reference ENCODE experiments with PubMed, bioRxiv, ClinicalTrials.gov, and GEO via linked references.
Security notes
100% local execution with no telemetry or analytics. Optional ENCODE credentials for restricted/unreleased data are encrypted at rest via the OS keyring (macOS Keychain, Linux Secret Service, Windows Credential Locker) with a Fernet fallback. Certificate verification is enforced (no verify=False), downloads are MD5-verified by default, and requests are rate limited to ENCODE's 10 req/sec policy. No data leaves the machine except queries to public APIs over HTTPS.
ENCODE Toolkit FAQ
Do I need ENCODE credentials to use it?
No. Most ENCODE data is public and requires no authentication. Credentials are only needed for restricted or unreleased data; when provided they are encrypted at rest in your OS keyring.
Can I install just the MCP server without the skills?
Yes. Run `claude mcp add encode -- uvx encode-toolkit` (or use npx/pip) to install only the 20 MCP tools. The 47 workflow skills and 7 pipelines come with the Claude Code plugin install.
Is it affiliated with the ENCODE Consortium?
No. It is an independent open-source toolkit by Dr. Alex M. Mawla that accesses the public ENCODE Project API; it is not an official ENCODE Consortium product.
Will batch downloads run automatically?
No. encode_batch_download runs in preview (dry_run) mode by default and only downloads when dry_run is set to false.
Alternatives to ENCODE Toolkit
Compare all alternatives →
Official MCP server providing persistent, file-backed knowledge-graph memory across sessions.
Structured step-by-step reasoning tool for breaking problems into revisable thought sequences.
Fully managed remote server for AWS docs, blogs, What's-New and Well-Architected guidance — no key.
Compare ENCODE Toolkit with: