Curated datasets
find_data_sources
Find Data Sources·v1.0.0·L1·read-only·MCP + REST·admitted 2026-09-19
Inputs
70 required
Sources
0
Known limits
0
Real answer
0.65spartial
What it answers
- 1Search the Vlada substrate catalog by keyword.
- 2Returns the matching data sources (commercial TiC, hospital HPT, Medicare, drug pricing, provider identity, curated marts, provenance registries) ranked by relevance.
- 3Compact by default (identity + queryable + claim ceiling + the exact describe_data_source call per hit); pass verbosity='full' for the previous full source_product_card per result.
- 4Paginates with limit (default 25, max 200) + offset; the response carries total_count, returned_count, and offset.
- 5Optional filters: {domain, stage, status, limit}.
- 6Agents call this first to discover what data Vlada has.
- 7Since 2026-09-02 the answer leads with DATA POINTS (`data_points`: the measure/dimension asked for, with its source, door, table.column and must-read trap) and the table cards follow as physical locations.
- 8Every hit carries `source_code` -- the one public code, which describe_data_source accepts verbatim -- alongside the table's `source_fqn`.
- 9Points and tables are ranked by ONE ranker (the authored data-point scorer).
- 10Retired tables are never returned; they appear only as `supersedes` on the live successor's card.
- 11BOUNDED (2026-09-18): the default call is compact and paged -- both the table cards and the data points come back a page at a time, each with its own total and next offset -- so a default call can never truncate.
- 12Pass verbosity='full' for the whole point record and the full source_product_card per hit.
Inputs (7)
| Name | Type | Required | Default | Accepts |
|---|---|---|---|---|
filters | any | optional | null | |
limit | any | optional | null | |
max_points | integer | optional | 3 | |
offset | integer | optional | 0 | |
query | string | optional | "" | |
verbosity | string | optional | "compact" | compact | full |
world | any | optional | null |
Call it
# MCP (https://mcp.vladahealth.com/mcp): the tool by name find_data_sources(query="medicare physician fee schedule", limit=5)
curl -X POST https://api.vladahealth.com/v1/tools/find_data_sources \
-H "Authorization: Bearer $VLADA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"query":"medicare physician fee schedule","limit":5}'
# the schema, no key
curl https://api.vladahealth.com/v1/tools/find_data_sources/schemaA real answer
customer seat, 2026-11-09·over REST·0.65s·status
partial·first 6,000 of 10,472 chars·verbatim{
"value": {
"query": "medicare physician fee schedule",
"filters": null,
"verbosity": "compact",
"status": "matched",
"retrieval_mode": "lexical",
"scope_verification": {
"status": "not_verified",
"basis": "catalog_match_only",
"geography": "not_verified",
"time_coverage": "not_verified",
"population": "not_verified",
"completeness": "not_verified"
},
"ranker": "authored_data_point_scorer",
"excludes": "retired",
"data_points": [
{
"rank": 1,
"world": "w2",
"data_point": {
"id": "w2.puf.physician_avg_medicare_allowed",
"name": "Medicare average allowed amount by provider and service",
"unit": "USD_per_service",
"kind": "measure"
},
"source": {
"id": "cms_puf_physician_other_practitioners",
"source_code": "cms_puf_physician_other_practitioners",
"title": "Medicare Physician & Other Practitioners public use files (by provider and service; by geography and service)",
"how_to_reach_it": "sql"
},
"location": {
"table": "medicare_silver.fact_physician_by_provider_service",
"column": "avg_medicare_allowed",
"variants": [
"paid=avg_medicare_payment",
"standardized=avg_medicare_standardized",
"submitted=avg_submitted_charge",
"services=tot_services",
"beneficiaries=tot_benes"
],
"required_filters": [
"is_current=true"
]
},
"trap": {
"must_read": "Always filter data_year and a state or code; averages of paid claims; null is suppressed.",
"ids": [
"data_year_pin",
"claims_average_not_fee_schedule",
"small_cell_suppressed_null",
"heavy_scan"
]
},
"next": "bounded query_substrate on medicare_silver.fact_physician_by_provider_service",
"fetch": "describe_data_source(source_fqn='cms_puf_physician_other_practitioners')",
"relevance": 51
},
{
"rank": 2,
"world": "w2",
"data_point": {
"id": "w2.pfs.national_allowed_amount",
"name": "PFS national allowed amount",
"unit": "USD",
"kind": "rate"
},
"source": {
"id": "cms_pfs_relative_value_files",
"source_code": "cms_pfs_relative_value_files",
"title": "Physician Fee Schedule relative value files (RVUs, indicators, conversion factor, GPCI, locality configuration)",
"how_to_reach_it": "sql"
},
"location": {
"table": "medicare_silver.fact_pfs_rvu",
"column": "conversion_factor",
"variants": [
"total_nonfacility_rvu=total_non_facility_rvu",
"total_facility_rvu=total_facility_rvu",
"status=status_code"
],
"required_filters": []
},
"trap": {
"must_read": "Compute RVU x conversion factor after filtering implausible rows; status_code says whether the code is payable; national only.",
"ids": [
"year_pin",
"implausible_conversion_factor_rows",
"locality_not_on_rvu"
]
},
"next": "call medicare_allowed",
"fetch": "describe_data_source(source_fqn='cms_pfs_relative_value_files')",
"relevance": 45
},
{
"rank": 3,
"world": "w2",
"data_point": {
"id": "w2.clfs.national_limit_amount",
"name": "CLFS national limitation amount",
"unit": "USD",
"kind": "rate"
},
"source": {
"id": "cms_clfs_national_rates",
"source_code": "cms_clfs_national_rates",
"title": "Clinical Laboratory Fee Schedule (national limitation amounts)",
"how_to_reach_it": "sql"
},
"location": {
"table": "medicare_silver.fact_clfs_national_rate",
"column": "national_limit_amount",
"variants": [],
"required_filters": []
},
"trap": {
"must_read": "Pin calendar_year and quarter; do not union with the legacy locality table.",
"ids": [
"quarter_pin"
]
},
"next": "bounded query_substrate on medicare_silver.fact_clfs_national_rate",
"fetch": "describe_data_source(source_fqn='cms_clfs_national_rates')",
"relevance": 42
}
],
"data_points_total_count": 3,
"data_points_returned_count": 3,
"data_points_detail_hint": "verbosity='full' returns grain, time pin, nulls, variants and basis for each point; describe_data_source(source_code) returns the table to query and a verified example.",
"match_count": 322,
"returned": 5,
"total_count": 322,
"returned_count": 5,
"offset": 0,
"limit": 5,
"results": [
{
"source_id": "cms_physician_by_provider_service",
"source_code": "cms_puf_physician_other_practitioners",
"title": "Medicare Physician & Other Practitioners \u2014 by Provider and Service (granular price)",
"published_source_code": "cms_puf_physician_other_practitioners",
"how_to_reach_it": "sql",
"domain": "medicare",
"status": "live",
"grain": "One row per (data_year, rendering NPI, HCPCS, place of service) \u2014 charge/allowed/paid.",
"queryable": true,
"not_queryable_reason": null,
"claim_ceiling": "queryable",
"fetch": "describe_data_source(source_fqn='medicare_silver.fact_physician_by_provider_service')",
"fetch_unavailable_reason": null,
"relevance": 1051,
"relevance_basis": "data_point",
"relevance_why": "holds data point w2.puf.physician_avg_medicare_allowed",
"world": "Medicare",
"view": "By doctor"
},
{
"source_id": "medicare_physician_payment_by_geo",
"source_code": "cms_puf_physician_other_practitioners",
"title": "Medicare Physician & Other Practitioners by Geography (avg allowed/payment per HCPCS)",
"published_source_code": "cms_puf_physician_other_practitioners",
"how_to_reach_it": "sql",
"domain": "medicare",
"status": "live",
"grain": "One row per (geography [National|State], HCPCS, place-of-service) per data year.",
"queryable": true,
"not_queryable_reason": null,
"claim_ceiling": "queryable",
"fetch": "describe_data_source(source_fqn='medicare_silver.fact_physician_payment_by_geo')",
"fetch_unavailable_reason":
…What comes back
| Field | Holds |
|---|---|
status | complete · partial · refused · failed · queued |
value | the shape below |
source · caveats · invariants_applied · response_hash | the public file and vintage; what to know before citing; the rules honoured; replayable |
refusal | code (15), message, recover_with |
{
"$defs": {
"Quality": {
"description": "Row-level quality signal. All flags precomputed at build time\n(stored on the gold mart) and passed through here.",
"properties": {
"is_outlier": {
"default": false,
"title": "Is Outlier",
"type": "boolean"
},
"is_ghost_candidate": {
"default": false,
"title": "Is Ghost Candidate",
"type": "boolean"
},
"n_similar_rates": {
"default": 0,
"title": "N Similar Rates",
"type": "integer"
},
"confidence": {
"default": 1,
"title": "Confidence",
"type": "number"
}
},
"title": "Quality",
"type": "object"
},
"Source": {
"description": "Cell-level provenance. Every served value traces back here.\n\n`snapshot_id` is the Iceberg snapshot the tool read from. Two calls\nat the same snapshot MUST produce byte-identical responses —\nthat's the content-addressed caching guarantee.",
"properties": {
"table": {
"title": "Table",
"type": "string"
},
"rate_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rate Id"
},
"source_files": {
"items": {
"type": "string"
},
"title": "Source Files",
"type": "array"
},
"snapshot_id": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Snapshot Id"
}
},
"required": [
"table"
],
"title": "Source",
"type": "object"
}
},
"properties": {
"value": {
"default": null,
"title": "Value"
},
"unit": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Unit"
},
"vintage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Vintage"
},
"source": {
"$ref": "#/$defs/Source"
},
"methodology": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Methodology"
},
"quality": {
"$ref": "#/$defs/Quality"
},
"invariants_applied": {
"items": {
"type": "string"
},
"title": "Invariants Applied",
"type": "array"
},
"caveats": {
"items": {
"type": "string"
},
"title": "Caveats",
"type": "array"
},
"response_hash": {
"default": "",
"title": "Response Hash",
"type": "string"
},
"semantic_version": {
"default": 1,
"title": "Semantic Version",
"type": "integer"
},
"tool_version": {
"default": "unknown",
"title": "Tool Version",
"type": "string"
},
"explanation": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Explanation"
},
"status": {
"default": "complete",
"title": "Status",
"type": "string"
},
"refusal": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Refusal"
},
"failure": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Failure"
},
"as_of": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "As Of"
},
"freshness_state": {
"default": "unknown",
"title": "Freshness State",
"type": "string"
}
},
"title": "CatalogResponse",
"type": "object"
}Sources
| Kind | Name |
|---|---|
| source | the catalog's card for each table it reads |
Known limits (0)
| Known limits |
|---|
| none recorded |
This page as markdown: /docs-md/tools/find_data_sources.md · every page in one file: /llms-full.txt