databazaar
Search and preview datasets publicly. Account-required full data via MCP.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
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": {
"databazaar": {
"command": "npx",
"args": [
"databazaar-mcp"
]
}
}
}Runnable packages
1.5.1stdioRemote endpoints
https://api.databazaar.io/mcpstreamable-httphttps://api.databazaar.io/mcp/publicstreamable-httpWhat it can do
Tool inventory
Tools (3)
🟢search_datasets(query, category, max_price, min_quality_score, pricing_type, ...)
Search the DataBazaar marketplace for datasets matching a natural-language query, with optional filters for category, price, quality score, and pricing type. Returns ranked listings with prices, quality scores, and checkout URLs. When results are empty, log_data_gap can post a bounty to signal demand to sellers.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Natural language search query describing the data needed"
},
"category": {
"type": "string",
"description": "Filter by category: geographic, pricing, sensor, images, text, financial, scientific, social, retail, other"
},
"max_price": {
"type": "number",
"description": "Maximum price in USD — omit to include all prices"
},
"min_quality_score": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Minimum assessed sample structure score (0-100); unassessed listings are excluded. See https://databazaar.io/quality for the rubric and limitations."
},
"pricing_type": {
"type": "string",
"enum": [
"buy_it_now",
"auction",
"hybrid",
"free"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢get_dataset(dataset_id)
Get full metadata for a specific dataset — schema, column counts, quality score, price anchoring, and a forwardable purchase pitch. Includes a checkout_url for one-click human purchase and a human_pitch field for operator messaging.
Input Schema
{
"type": "object",
"properties": {
"dataset_id": {
"type": "string",
"format": "uuid",
"description": "The dataset ID to retrieve"
}
},
"required": [
"dataset_id"
],
"additionalProperties": false
}🟢preview_sample(dataset_id, question)
Preview sample rows of a dataset to verify it contains the expected columns, format, and quality. Returns a signed download URL for ~50 rows plus the schema. Pass an optional question to get a synthesized answer from the sample (e.g. "average price in 2024") — no purchase required.
Input Schema
{
"type": "object",
"properties": {
"dataset_id": {
"type": "string",
"format": "uuid",
"description": "The dataset ID to preview"
},
"question": {
"type": "string",
"description": "Optional natural-language question to answer from the sample (e.g. \"average rent in SF\", \"count of records per state\"). Returns a synthesized_answer field with deterministic aggregates if the question matches a simple pattern."
}
},
"required": [
"dataset_id"
],
"additionalProperties": false
}Community
Evidence