Mostly Right
Search, sample and query open reproducible datasets published as immutable Parquet with schemas.
Should I use this
Quality & Safety
A
Findings (1)
- LOWin fetch
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
~15,490Tokens (tool definitions)
~1.5 KBTypical response size
Significant attention impact (12.10% of 128k context)
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"datasets": {
"url": "https://mostlyright.md/api/mcp"
}
}
}Remote endpoints
https://mostlyright.md/api/mcpstreamable-httpWhat it can do
Tool inventory
No publishable tool enumeration has been recorded.
Recommended Prompts
search_research
Search for information about [topic] using Mostly Right
Expected tools:
search_datasetsfind_specific
Find [specific item] using Mostly Right
Expected tools:
search_datasetsretrieve_data
Get details about [item] from Mostly Right
Expected tools:
get_datasetfetch_info
Fetch [information type] using Mostly Right
Expected tools:
get_datasetlist_items
List all [items] available in Mostly Right
Expected tools:
list_tablesCommunity
Evidence
Recent observations
failed observationversion not recorded—
verifiedversion not recorded38 tools
verifiedversion not recorded38 tools
verifiedversion not recorded38 tools
verifiedversion not recorded38 tools