get_drug_source_inventory

Get Drug Source Inventory

What it answers

Discover the drug substrate. Returns one row per drug_silver table (and per expected-but-missing source) with: domain, row_type, row count, time range, refresh cadence, next expected refresh, MCP tool(s) exposing the table, quality signals (dup_pk groups + null_bronze count + last quality-check outcome), cadence-drift and agent-usage signals, and the current Iceberg snapshot id reader at last inventory refresh.

Filters: domain (spuf / drug_identity / regulatory / etc.), row_type (existing | expected_missing | deprecated | blocked_restricted), refresh_cadence, has_mcp_tool (bool — true=only MCP-exposed, false=dark-zone), quality_failing_only (bool), production_only (bool, default true), table_name (exact match), expected_source_id (filter negative-space rows).

This is the meta-tool for substrate discovery. Call FIRST to plan which other tools to call, to detect stale tables before relying on them, OR to find sources the substrate doesn't yet have (negative-space awareness via row_type='expected_missing' — a v2 addition over MA's v1).

v2 additions over MA's get_ma_source_inventory: per-row quality signals (closes blind spot: existence ≠ correctness), snapshot pinning columns (closes blind spot: inventory ≠ current state), and negative-space rows for sources we expect but haven't ingested yet. v3 additions: cadence drift and trailing 7-day agent query counts.

SOURCE: drug_silver.dim_drug_source_inventory — refreshed daily.

Inputs

acknowledge_era_break

boolean · optional

default: false

domain

string · optional

expected_source_id

string · optional

has_mcp_tool

boolean · optional

production_only

boolean · optional

default: true

quality_failing_only

boolean · optional

refresh_cadence

string · optional

row_type

string · optional

table_name

string · optional

Call it

From an agent: connect the Vlada MCP once (one click for Claude, ChatGPT, Cursor, VS Code) and ask in plain English; the agent selects get_drug_source_inventory when the question fits. From code: the same tool over REST with an API key. The schema endpoint needs no key.

curl -X POST https://api.vladahealth.com/v1/tools/get_drug_source_inventory \
  -H "Authorization: Bearer $VLADA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

curl https://api.vladahealth.com/v1/tools/get_drug_source_inventory/schema      # the JSON schema, no auth
# MCP endpoint (Streamable HTTP): https://mcp.vladahealth.com/mcp

What comes back

Typed rows plus provenance on every answer: the public source file, its vintage, the methodology, and a response_hash you can replay. Prove and replay tools turn any number into a re-runnable receipt. A number the data cannot support comes back as “not in the data”, never as zero.

Sources behind it

tables: drug_silver.dim_drug_source_inventory

Known limits

drug_inventory_quality_check_stale

As of the 2026-09-19 build of the served surface · machine-readable catalog · the live server may run a different version; the schema endpoint above is authoritative for what is deployed.