Skip to main content
Glama

UCSC Genome Browser MCP Server

by hlydecker
GitHub
Python
MIT License
  • Apple
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

UCSC Genome Browser MCP Server

A Model Context Protocol (MCP) server that provides comprehensive access to the UCSC Genome Browser API. This server enables LLM applications to query genomic data, sequences, tracks, and metadata from the UCSC Genome Browser.

Features

This MCP server exposes 12 tools that cover all major UCSC Genome Browser API endpoints:

Listing & Discovery Tools

  • find_genome - Search for genomes using keywords, accession IDs, or organism names

  • list_public_hubs - List all available public track hubs

  • list_ucsc_genomes - List all UCSC database genomes

  • list_genark_genomes - List GenArk assembly hub genomes

  • list_hub_genomes - List genomes from a specific hub

  • list_files - List downloadable files for a genome

  • list_tracks - List data tracks in a genome or hub

  • list_chromosomes - List chromosomes in a genome or track

  • list_schema - Get schema/field definitions for a track

Data Retrieval Tools

  • get_sequence - Retrieve DNA sequences from genomes

  • get_track_data - Get track data (genes, variants, annotations, etc.)

  • search_genome - Search within a genome assembly

Installation

Prerequisites

  • Python 3.10 or higher

  • pip

Install from source

# Clone or download the repository cd ucsc-genome-mcp-server # Install in development mode pip install -e .

Required Dependencies

  • mcp>=0.9.0 - Model Context Protocol SDK

  • httpx>=0.27.0 - HTTP client for API requests

Usage

Running the Server

The server communicates over stdio, following the MCP protocol:

python ucsc_genome_mcp_server.py

Configuration with Claude Desktop

Add this to your Claude Desktop configuration file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{ "mcpServers": { "ucsc-genome-browser": { "command": "python", "args": ["/path/to/ucsc_genome_mcp_server.py"] } } }

Tool Examples

1. Find Genomes

Search for dog genomes:

{ "query": "dog" }

Search with advanced operators:

{ "query": "+white +rhino* -southern", "browser": "mustExist" }

2. List Available Tracks

List all tracks for human genome (hg38):

{ "genome": "hg38" }

List tracks without container information:

{ "genome": "hg38", "track_leaves_only": true }

3. Get DNA Sequence

Get entire mitochondrial chromosome:

{ "genome": "hg38", "chrom": "chrM" }

Get specific region:

{ "genome": "hg38", "chrom": "chrM", "start": 4321, "end": 5678 }

Get reverse complement:

{ "genome": "hg38", "chrom": "chrM", "start": 4321, "end": 5678, "reverse_complement": true }

4. Get Track Data

Get gene annotations for a region:

{ "genome": "hg38", "track": "knownGene", "chrom": "chr1", "start": 47000, "end": 48000 }

Get track data from an assembly hub:

{ "hub_url": "http://hgdownload.gi.ucsc.edu/hubs/mouseStrains/hub.txt", "genome": "CAST_EiJ", "track": "assembly", "chrom": "chr1" }

5. Search Within a Genome

Search for BRCA1 in human genome:

{ "search": "brca1", "genome": "hg38" }

Search only in help documentation:

{ "search": "bigBed", "genome": "hg38", "categories": "helpDocs" }

API Details

Base URL

All requests go to: https://api.genome.ucsc.edu

Rate Limits

  • Recommended: Maximum 1 request per second

  • The API has a botDelay system to prevent overload

  • Excessive queries may result in restricted access

Coordinate Systems

  • Start coordinates: 0-based (first base is 0)

  • End coordinates: 1-based (exclusive)

  • Example: start=0, end=10 retrieves the first 10 bases

Supported Track Types

The get_track_data tool supports these track types:

  • bed, bigBed, bigWig

  • genePred, bigGenePred

  • bigChain, bigPsl, bigMaf

  • narrowPeak, bigNarrowPeak

  • wiggle/wig, barChart/bigBarChart

  • interact/bigInteract

  • And many more...

Advanced Features

Working with Large Datasets

For tracks with over 1 million items, use pagination:

  1. Query by chromosome:

{ "genome": "hg19", "track": "knownGene", "chrom": "chr1" }

  1. Use start/end coordinates for smaller regions:

{ "genome": "hg19", "track": "knownGene", "chrom": "chr1", "start": 1000000, "end": 2000000 }

Working with Track Hubs

Track hubs allow accessing external genomic data:

{ "hub_url": "http://hgdownload.gi.ucsc.edu/hubs/mouseStrains/hub.txt", "genome": "CAST_EiJ", "track": "ensGene", "chrom": "chr1" }

Error Handling

The server handles various error conditions:

  • HTTP errors (404, 500, etc.)

  • Invalid parameters

  • Non-existent genomes/tracks/chromosomes

  • Request timeouts (30 second default)

Errors are returned as text responses with descriptive messages.

Use Cases

This MCP server enables LLM applications to:

  1. Genomic Research: Query gene locations, sequences, and annotations

  2. Variant Analysis: Retrieve SNP and variant data

  3. Comparative Genomics: Access data from multiple species

  4. Sequence Analysis: Get DNA/RNA sequences for analysis

  5. Data Discovery: Find available datasets and assemblies

  6. Educational: Learn about genomics through interactive queries

API Documentation

For complete API documentation, visit: https://genome.ucsc.edu/goldenpath/help/api.html

License

This project interfaces with the UCSC Genome Browser, which has its own terms of use: https://genome.ucsc.edu/conditions.html

Support

For issues with the UCSC Genome Browser API, contact UCSC. For issues with this MCP server, please file an issue in the repository.

Development

Project Structure

. ├── ucsc_genome_mcp_server.py # Main server implementation ├── pyproject.toml # Project metadata and dependencies └── README.md # This file

Adding New Tools

To add new endpoints:

  1. Add the tool definition in list_tools()

  2. Add the handler in call_tool()

  3. Update this README with examples

Testing

Test individual endpoints manually:

# Using curl curl -L 'https://api.genome.ucsc.edu/list/ucscGenomes' # Using wget wget -O- 'https://api.genome.ucsc.edu/getData/sequence?genome=hg38;chrom=chrM;start=4321;end=5678'

Changelog

Version 0.1.0

  • Initial release

  • Support for all major UCSC Genome Browser API endpoints

  • 12 tools covering listing, discovery, and data retrieval

  • Full documentation and examples

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Provides comprehensive access to the UCSC Genome Browser API, enabling queries of genomic data, DNA sequences, gene annotations, variants, and metadata across multiple species and assemblies.

  1. Features
    1. Listing & Discovery Tools
    2. Data Retrieval Tools
  2. Installation
    1. Prerequisites
    2. Install from source
    3. Required Dependencies
  3. Usage
    1. Running the Server
    2. Configuration with Claude Desktop
  4. Tool Examples
    1. 1. Find Genomes
    2. 2. List Available Tracks
    3. 3. Get DNA Sequence
    4. 4. Get Track Data
    5. 5. Search Within a Genome
  5. API Details
    1. Base URL
    2. Rate Limits
    3. Coordinate Systems
    4. Supported Track Types
  6. Advanced Features
    1. Working with Large Datasets
    2. Working with Track Hubs
  7. Error Handling
    1. Use Cases
      1. API Documentation
        1. License
          1. Support
            1. Development
              1. Project Structure
              2. Adding New Tools
              3. Testing
            2. Changelog
              1. Version 0.1.0

            New MCP Servers

            MCP directory API

            We provide all the information about MCP servers via our MCP API.

            curl -X GET 'https://glama.ai/api/mcp/v1/servers/hlydecker/ucsc-genome-mcp'

            If you have feedback or need assistance with the MCP directory API, please join our Discord server