io.github.rpconroy/gdex-mcp
MCP server for the GDEX (Geoscience Data Exchange) data portal: datasets, files, metrics, subsetting
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http gdex-mcp 'https://gdex-mcp.k8s.ucar.edu/mcp'
{
"mcpServers": {
"gdex-mcp": {
"type": "http",
"url": "https://gdex-mcp.k8s.ucar.edu/mcp"
}
}
}
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
GDEX MCP Server
An MCP (Model Context Protocol) server exposing the GDEX (Geoscience Data Exchange) REST API as tools for LLM clients — dataset discovery/metadata, file listings, data access links, ARCO variables, portal/dataset metrics, staff contacts, and authenticated subsetting-request workflows.
Running locally
pip install -e .
gdex-mcp
Then point your MCP client (Claude Desktop, Claude Code, etc.) at the
gdex-mcp command. Configuration is via environment variables or a .env
file — see CLAUDE.md's Configuration section. Most tools need no
configuration at all; set GDEX_TOKEN only if you'll use the
subsetting-request tools (list_request_statuses, check_request_status,
get_request_files, submit_subset_request, submit_and_wait_for_request,
purge_request).
Running as a shared service
Set GDEX_MCP_TRANSPORT=streamable-http (see Dockerfile) to run this as a
network-reachable service instead of a local stdio subprocess. In that mode,
callers using the subsetting-request tools pass their own GDEX token as an
Authorization: Token <token> header on each request rather than relying on
a shared GDEX_TOKEN — see CLAUDE.md's "Two transports" section for how
that's wired.
Docker
# Build the image
docker build -t gdex-mcp .
# Run the container
docker run -d --name gdex-mcp -p 8080:8080 gdex-mcp
MCP requests go to http://localhost:8080/mcp.
# Stop and remove the container
docker stop gdex-mcp && docker rm gdex-mcp
Deployment
A merged PR to main triggers the GitHub Actions workflow, which runs the
test suite (pip install -e ".[test]" && pytest) and then builds a
new Docker image and pushes it to Harbor
(hub.k8s.ucar.edu/gdex_mcp/gdex-mcp). The app is deployed to
Kubernetes via the Helm chart in app-chart/ — see CLAUDE.md's Deployment
section for how this follows gdex-web-services' conventions.
# Deploy with Helm
helm upgrade --install gdex-mcp ./app-chart -n <namespace>
# Deploy a test instance
helm upgrade --install gdex-mcp ./app-chart -n <namespace> --set testName=<your-name>
MCP Registry
gdex-mcp is published to the official MCP Registry
as io.github.rpconroy/gdex-mcp (see server.json), not io.github.NCAR/gdex-mcp.
Publishing under the NCAR org namespace kept failing with a 403 even after
making org membership public — a known, unresolved issue with the registry's
org-membership check (see modelcontextprotocol/registry#1537
and #1649),
suspected to be an org-admin-side GitHub OAuth App access restriction rather
than anything on our end. .github/workflows/publish-mcp-registry.yaml
publishes new versions on v* tags; it uses PAT auth (MCP_GITHUB_TOKEN
secret) instead of GitHub OIDC because this repo is NCAR-owned, so Actions
OIDC always asserts repository_owner: NCAR and can't authenticate as the
personal rpconroy namespace. Once NCAR org access is sorted out, moving to
io.github.NCAR/gdex-mcp means publishing a new registry entry (the registry
has no rename support) and switching the workflow back to login github-oidc.
Documentation
CLAUDE.md has the full picture: architecture, conventions to follow when
adding tools, the two transport modes, and deployment. Read it before making
changes here.
Frequently asked questions
What is io.github.rpconroy/gdex-mcp?
MCP server for the GDEX (Geoscience Data Exchange) data portal: datasets, files, metrics, subsetting
How do I install io.github.rpconroy/gdex-mcp?
It runs as a remote server. In Claude Code: claude mcp add --transport http gdex-mcp 'https://gdex-mcp.k8s.ucar.edu/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does io.github.rpconroy/gdex-mcp need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is io.github.rpconroy/gdex-mcp open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains io.github.rpconroy/gdex-mcp?
It is published by NCAR. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.