Encode Toolkit by Ammawla is a free MCP server built with Python 3.10+ for bioinformaticians and genomics researchers. It connects to ENCODE genomic data and integrates with 14 external public genomics databases, including GTEx and ClinVar. The toolkit offers 20 MCP tools for data search and download, alongside 47 guided skills for multi-database workflows. It is compatible with Claude Code and any MCP-compatible client, providing a focused platform for genomic data exploration and analysis.

What does Encode Toolkit connect to?

Encode Toolkit functions as an MCP server, establishing connections to ENCODE genomic data. It significantly expands its utility by integrating with 14 external public genomics databases. These crucial resources include prominent platforms such as GTEx, ClinVar, GWAS Catalog, and PubMed. This extensive connectivity allows users to efficiently access and combine information from diverse sources, thereby supporting a broad spectrum of genomic research requirements. The server’s core purpose is to act as a centralized hub for accessing and manipulating this widely distributed genomic information.

Core features and tools

The Encode Toolkit offers 20 distinct MCP tools specifically designed for ENCODE data search and download operations. In addition to these tools, it provides 47 guided skills, which are tailored for executing complex multi-database workflows. While the specific names of individual callable tools are not detailed, examples of their practical functionality include downloading BED files directly from an experiment and effectively tracking experiments alongside their associated publications. These capabilities enable users to perform precise actions on genomic data, ranging from basic retrieval to intricate analytical sequences across multiple integrated databases.

Who is it for?

Encode Toolkit is primarily intended for bioinformaticians and genomics researchers. It supports several concrete workflows, such as searching for histone ChIP-seq experiments based on tissue, target, or biosample. The toolkit also assists in cross-referencing GWAS variants with islet enhancers and ClinVar pathogenicity data. Furthermore, it enables users to run ChIP-seq pipelines while adhering to ENCODE-standard QC thresholds, making it a specialized asset for those engaged in detailed genomic data analysis. Skip this if your work does not involve detailed genomic data analysis or multi-database queries.

How to get started

No credentials are required for Encode Toolkit, as it utilizes public REST APIs and E-utilities for data access.

Use cases

• Searching for histone ChIP-seq experiments by tissue, target, or biosample.
• Cross-referencing GWAS variants with islet enhancers and ClinVar pathogenicity.
• Running ChIP-seq pipelines with ENCODE-standard QC thresholds.

Encode Toolkit provides a specialized MCP server for genomic data, connecting to ENCODE and 14 other public databases. It offers a collection of tools and guided skills tailored for bioinformaticians and genomics researchers. The server simplifies access to complex genomic information without requiring API keys, making it readily usable. Its compatibility with Claude Code and other MCP clients broadens its application.