Mostly Right for Grok
md.mostlyright/datasets
Search, sample and query open reproducible datasets published as immutable Parquet with schemas.
client:Grok
transport:streamable-http
tools:38
Install Mostly Right in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"datasets": {
"type": "http",
"url": "https://mostlyright.md/api/mcp"
}
}
}Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs
What Grok can do once it is connected
- search_datasets
- get_dataset
- list_tables
- get_table_schema
- sample_rows
- get_download_instructions
- get_access_instructions
- search
- fetch
- query_table
- catalog_search
- list_connected_datasets
- connect_dataset
- create_dataset
- update_dataset
- list_my_datasets
- get_my_dataset
- register_recipe
- propose_revision
- replay_run
- start_run
- confirm_run
- approve_full_run
- cancel_run