MCP.so
Sign In

Encode Toolkit

@ammawla

About Encode Toolkit

MCP server and Claude Plugin for a full ENCODE Project genomic data and analysis toolkit — search, download, track, and analyze functional genomics experiments

Basic information

Category

Developer Tools

License

AGPL-3.0

Runtime

python

Transports

stdio

Publisher

ammawla

Submitted by

Dr. Alex M. Mawla, PhD

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "encode-toolkit": {
      "command": "npx",
      "args": [
        "encode-toolkit"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Encode Toolkit?

Encode Toolkit is an MCP server that provides natural language access to ENCODE genomic data, cross-references 14 external databases, runs 7 analysis pipelines, and generates publication-ready methods with full provenance tracking. It is designed for bioinformaticians and genomics researchers who want to query and analyze public genomic datasets directly from Claude Code or any MCP-compatible client.

How to use Encode Toolkit?

The recommended installation is as a Claude Code plugin: run /plugin marketplace add ammawla/encode-toolkit then /plugin install encode-toolkit inside a new Claude Code session. Alternatively, install via uvx encode-toolkit and add to your MCP client config, or use npx encode-toolkit or pip install encode-toolkit for standalone use.

Key features of Encode Toolkit

  • 20 MCP tools for ENCODE data search and download
  • 47 guided skills for multi-database workflows
  • Integration with 14 public genomics databases
  • 7 built-in analysis pipelines (ChIP-seq, ATAC-seq, etc.)
  • Full provenance and audit trail for all operations
  • No telemetry, no API keys required
  • 98% test coverage with 568 passing tests

Use cases of Encode Toolkit

  • Search for histone ChIP-seq experiments by tissue, target, or biosample
  • Cross-reference GWAS variants with islet enhancers and ClinVar pathogenicity
  • Download BED files from an experiment with MD5 verification
  • Run a ChIP-seq pipeline with ENCODE-standard QC thresholds
  • Generate a methods section with citations and provenance chain

FAQ from Encode Toolkit

What does Encode Toolkit require to run?

The server requires Python 3.10+ and can be run with uvx, npx, or a direct pip install. No API keys or environment variables are needed because it uses public REST APIs and E-utilities.

Which databases does Encode Toolkit connect to?

It connects to 14 databases: ENCODE, GTEx, ClinVar, GWAS Catalog, JASPAR, CellxGene, gnomAD, Ensembl, UCSC Genome Browser, GEO, PubMed, bioRxiv, ClinicalTrials.gov, and Open Targets.

Does Encode Toolkit collect usage data or telemetry?

No, the server explicitly states "security: no telemetry" and follows a trust-minimizing design.

Can I use Encode Toolkit with editors other than Claude Code?

Yes, it works with Claude Desktop, VS Code / Copilot, Cursor, and Windsurf by adding the appropriate MCP JSON configuration.

Comments

More Developer Tools MCP servers