Data catalogue
Find datasets, series, publications and extracts across the marketplace.
- Warehouse rows
- 6.17B
- Structured DB
- 1,711.35 GB
- Live data store
- 189.73 GB
- Data tables
- 1,03,091
- Publications & data products
- 1,749
About these figures
BigQuery reports 6,167,191,751 physical rows across 89 native base tables in 9 catalogue warehouses, measured on . Structured DB measures logical bytes across the same tables. The headline excludes 22 verified staging and backup tables with 365,935,268 rows and 57.49 GB of logical storage. Separate publisher editions can contain overlapping observations.
The earlier 40-MCP inventory reported 1,115,017,091 records across warehouses, files and upstream sources, including 811,051,329 upstream survey records from MoSPI NADA.
Live data store measures 189.73 GB of live catalogue objects across 39 Cloud Storage buckets, measured on .
UNCTAD ingestion files account for 153.97 GB of additional live storage. Retained soft-deleted objects account for 109.84 GB. Raw publisher archives and their corresponding BigQuery tables are measured in their respective storage layers.
Data tables counts 1,03,091 publisher tables held across the marketplace MCPs, measured in each MCP's own store on 2026-11-10: one table, sheet, dataflow, report section or API dataset in one edition counts once, the way data.gov.in counts resources. Raw copies, backups and archive duplicates are not counted twice. They belong to 1,749 publications and data products — six Economic Survey reports are one publication — which hold 10,664 editions, 8,62,701 series and 19,717 documents. India Intelligence and Survey chapter packs are built from these MCPs and are not added. Geo-Spatial can also reach 2,36,742 data.gov.in resources live; they are not held and not counted.
The search index includes 18,933 datasets (tables, survey studies and map layers) and 493 individually indexed series. Separate live and archived access routes can have their own entries. These figures apply across the catalogue, regardless of filters.
Dataset Builder
33 results
Coverage unknown. Describe a dataset, get a multi-tab Excel workbook — retrieved from the data warehouse, official releases and filings, with the source of every cell.
preview table
Quick look at filled values: entity × last N periods for one metric (or each).
reconcile
Fill each cell from its best candidate (source tier, then date, then locator precision), keep disagreeing candidates as conflicts, compute derived metrics.
register source
Plug an MCP in as a data source — e.g. a SQL query MCP (capability sql_query), a statistics API (structured_data), a web search MCP. HTTP (`url`, `headers`) or stdio (`command`, `args`); ${ENV} references allowed in headers/env; capabilities inferred from its tools if omitted.
remove source
Unregister a source (the built-in claude-web source is disabled instead).
resolve entities
Verify and complete the entity list — official names, aliases, identifiers — against current sources, when the set is defined by a rule ("top 5 by revenue").
retrieval status
Per-task status, calls used, values accepted/rejected, and unavailable sources.
run retrieval
Run retrieval tasks as bounded agents (default: all planned tasks, in parallel). Every recorded value passes the value gate; rejected values are parked with a reason.
set value
Manual override for one cell (value=None clears the override). Logged with the note and shown as 'override' in the workbook.
start dataset job
Start a full build in the background and return at once. Pass `dataset_id` to build a dataset whose spec you already reviewed with define_dataset_spec. Poll get_dataset_job(dataset_id) — it long-polls.
submit values
Host mode: submit values for a task — each {entity, metric, period, value, unit, basis, source_type, source_url|source_ref, source_title, published, locator}, AS PRINTED. Each is gated; rejected ones come back with the reason.
to insight article
Hand the finished dataset to the Insight Generation MCP to research and write an article answering `question`. Returns its job's session_id (poll it there with get_article_job).
update dataset spec
Edit the Spec: top-level keys in `patch` replace the stored ones (lists replace wholesale), e.g. {"entities": [...]}, {"periods": {"start": "Q1 FY22"}}, {"metrics": [...]}, {"conflict_tolerance_pct": 1}. Re-validated on save.
validate dataset
Completeness per metric, derived-vs-reported mismatches, range checks, fraction-vs- percent slips, scale jumps and outliers against each series' own history.
Inventory snapshot 15 Nov 2026. Publisher dates and individual source checks can differ.