Skip to main content

Registry of Open Data on AWS (RODA) MCP Server

Model Context Protocol (MCP) server for discovering and exploring datasets from the Registry of Open Data on AWS (RODA). The Registry hosts hundreds of publicly available datasets including climate data, genomics, satellite imagery, and more on Amazon Simple Storage Service (S3).

Features

  • Discover datasets across 1,000+ open datasets on AWS
  • Search by keyword, organization, license, or topic in natural language
  • Find related datasets and explore by domain
  • Always surfaces license information
  • Preview and sample datasets for early evaluation
  • Curated next steps on how to access datasets
  • For public datasets without controlled access:
    • preview S3 bucket structure
    • sample file directly in conversation

Basic Usage

Ask your AI assistants in natural language:

  • "What open data are on AWS?"
  • "Show me datasets related to land surface temperature."
  • "Get more details about 1000 Genomes."
  • "Preview the file structure of CHIRPS and sample a file."

For more example on how to use the MCP server, check out Example Usage.

[!NOTE] Each dataset on RODA has specific license terms. Please review them before accessing or using the data.

Prerequisites

  1. Install uv from Astral
  2. Install Python 3.10+ using uv python install 3.10

Available Tools

Tool Description
search_datasets Search by keyword with optional filters for tags, organization, and license type
list_datasets List all datasets with optional tag filtering
get_dataset_details Get complete details for a specific dataset including resources and access info
discover_by_organization Find datasets managed by a specific organization (e.g., NASA, NOAA)
discover_by_license Find datasets by license type (e.g., Creative Commons, MIT)
find_related_datasets Find datasets related to a given dataset based on shared tags
get_knowledge_base_stats Get registry statistics including top tags, organizations, and resource types
preview_dataset Show S3 bucket structure for datasets (no download, no AWS account needed). This is only available for public datasets without controlled access. You should review and agree to the dataset license before previewing datasets.
sample_dataset Read the first 100KB of a specific file from a public dataset's S3 bucket. This is only available for public datasets without controlled access. You should review and agree to the dataset license before sampling datasets.
search_stac_endpoints Find datasets with STAC (SpatioTemporal Asset Catalog) API endpoints

Datasets on the Registry fall into three access tiers, due to different compliance reasons:

  • Open and free; hosted in a public S3 bucket and don't require AWS account to use
  • Open, but require AWS credentials and requester pay
  • Controlled access, particularly in health domains, and requires additional steps to access the datasets

For the datasets that are open and free, we offer a preview into S3 buckets, as well as capability to sample a file to help users quickly evaluate the datasets. For other datasets, we provide access instructions to users on how to access the datasets.

To learn more about how we designed this MCP server, check out High-Level Design.

Setup

Using uv

Configure the MCP server in your MCP client configuration (e.g., for Kiro, edit ~/.kiro/settings/mcp.json):

For Linux/MacOS users:

{
  "mcpServers": {
    "awslabs.roda-mcp-server": {
      "command": "uvx",
      "args": [
        "awslabs.roda-mcp-server@latest"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

For Windows users:

{
  "mcpServers": {
    "awslabs.roda-mcp-server": {
      "disabled": false,
      "timeout": 60,
      "type": "stdio",
      "command": "uv",
      "args": [
        "tool",
        "run",
        "--from",
        "awslabs.roda-mcp-server@latest",
        "awslabs.roda-mcp-server.exe"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Using Claude Code CLI

# Add RODA MCP
claude mcp add roda-mcp uvx awslabs.roda-mcp-server@latest

# List installed server
claude mcp list

Security

Check out Security for security considerations on this MCP server.

License

Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.

Licensed under the Apache License, Version 2.0 (the "License").

Disclaimer

This roda-mcp-server package is provided "as is" without warranty of any kind, express or implied, and is intended for development, testing, and evaluation purposes only. We do not provide any guarantee on the quality, performance, or reliability of this package. LLMs are non-deterministic and they make mistakes, we advise you to always thoroughly test and follow the best practices of your organization before using these tools on customer facing accounts. Users of this package are solely responsible for implementing proper security controls and MUST use AWS Identity and Access Management (IAM) to manage access to AWS resources. You are responsible for configuring appropriate IAM policies, roles, and permissions, and any security vulnerabilities resulting from improper IAM configuration are your sole responsibility. By using this package, you acknowledge that you have read and understood this disclaimer and agree to use the package at your own risk.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

awslabs_roda_mcp_server-0.1.4.tar.gz (267.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

awslabs_roda_mcp_server-0.1.4-py3-none-any.whl (23.2 kB view details)

Uploaded Python 3

File details

Details for the file awslabs_roda_mcp_server-0.1.4.tar.gz.

File metadata

  • Download URL: awslabs_roda_mcp_server-0.1.4.tar.gz
  • Upload date:
  • Size: 267.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for awslabs_roda_mcp_server-0.1.4.tar.gz
Algorithm Hash digest
SHA256 d948e68cd64619fc2ef42051b622e613c150ae50afbb09ab4040a52093f3a287
MD5 65fe0eee0fe40b5d19459c48894e89f5
BLAKE2b-256 029589244c5ed2030927aa679c2a00bc2e5f41fe7764f2f4e9a0de768659daa5

See more details on using hashes here.

Provenance

The following attestation bundles were made for awslabs_roda_mcp_server-0.1.4.tar.gz:

Publisher: release.yml on awslabs/mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file awslabs_roda_mcp_server-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for awslabs_roda_mcp_server-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 2281763d0a88eee3697c8501da1257596856adc4d62fa22207f39f9a83bc40b0
MD5 b71145ae31c1209d815aae3509ce828e
BLAKE2b-256 a9df1d6532d5e7f7d33a3767e5a570e4748ee073c454865d40206f6acff8540e

See more details on using hashes here.

Provenance

The following attestation bundles were made for awslabs_roda_mcp_server-0.1.4-py3-none-any.whl:

Publisher: release.yml on awslabs/mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.1.5

2 files

This release

0.1.4 This release

2 files

0.1.3

2 files

0.1.2

2 files

0.1.1

2 files

0.0.0

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page