Encode Toolkit

Name: Encode Toolkit
Author: ammawla

@ammawla

关于 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

#bioinformatics #ai #encode-ai-agents #claude-bioinformatics-tool #mcp-server #claude-code #claude-mcp #claude-code-mcp #claude-code-plugin #claude-skills #claude-code-skills #claude-plugin #ai-bio

基本信息

分类

开发工具

许可证

AGPL-3.0

运行时

python

传输方式

stdio

发布者

ammawla

提交者

Dr. Alex M. Mawla, PhD

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

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.