India · New Delhi · See the India profile
India's National Statistics Office launched a beta Model Context Protocol server on 6 February 2026, letting AI tools query official statistics directly. An independent test verified inflation and unemployment figures but found gaps in flagging methodology changes.
On 6 February 2026, India's National Statistics Office (NSO), part of the Ministry of Statistics and Programme Implementation (MoSPI), launched a beta Model Context Protocol (MCP) server on its eSankhyiki portal — the country's platform for official statistics. MCP is an open protocol that lets AI assistants such as Claude or ChatGPT query a data source directly and conversationally, instead of a user manually navigating an API or downloading files; India's beta initially exposed seven datasets (the Periodic Labour Force Survey, Consumer Price Index, Index of Industrial Production, Wholesale Price Index, National Accounts Statistics and others) and had expanded to 21 data products within months, according to NSO's own press releases and community trackers. The source code is published on GitHub under an MIT licence.
An independent test by a technical blogger checked three specific queries against official sources: December 2025 inflation figures (rural 0.76%, urban 2.03%) matched the official press release exactly; a Bihar unemployment rate of 4.8% for July-September 2025 matched the PLFS Quarterly Bulletin; and a textile Wholesale Price Index comparison between August 2024 and August 2023 aligned with PIB releases. The same review, however, flagged real limitations: the underlying LLM did not adequately warn that India's Consumer Price Index had changed base years (from 2011-12 to 2023-24) in ways that affect comparability, could not efficiently retrieve complete long historical series, and does not generate reproducible API calls that a user could independently verify.
MoSPI frames the server as part of a broader Data Innovation Lab programme — which had signed 17 MoUs with outside institutions and had two of twelve identified AI use cases in production by January 2026 — aimed at supporting India's 'Viksit Bharat' data-infrastructure goals. As a beta pilot covering a fraction of India's total statistical output, its main open question is whether the accuracy the independent tester found on simple lookups holds up as coverage and query complexity grow.
Read the full analysis: https://github.com/nso-india/esankhyiki-mcp
Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.
Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.
Where this practice's information was retrieved from, and when.
Singapore
Singapore's Department of Statistics launched SANDRA, a semantic-search AI chatbot for querying its 2,400-table SingStat Table Builder in plain English. …
Luxembourg
The EU's open-data portal auto-translates harvested dataset metadata into all 24 official EU languages via the Commission's eTranslation engine — …
Lithuania
Lithuania's State Data Agency runs a Palantir Foundry data lake connecting ~500 government systems, with 900+ open tables and 238 …
South Korea
Seoul's Data Hub uses a retrieval-augmented generative-AI chatbot to let residents search 8,100+ open datasets in plain Korean; in its …
Open full copilot Grounded in cited practices — always check the sources.