MoSPI's MCP Server — AI-Ready Natural-Language Access to India's Official Statistics

In February 2026, India's National Statistical Office (part of the Ministry of Statistics and Programme Implementation, MoSPI) launched a beta Model Context Protocol (MCP) server for its eSankhyiki statistics portal, developed with nonprofit partner Bharat Digital, allowing AI assistants such as Claude or ChatGPT to query official economic and social statistics through natural language with built-in source attribution.

Users can add mcp.mospi.gov.in as a custom connector in Claude or ChatGPT, including on free tiers, to ask plain-language questions about employment, prices, industrial output or GDP. The beta phase covers seven of about 19 planned statistical products — including the Periodic Labour Force Survey, Consumer Price Index, Annual Survey of Industries, Index of Industrial Production, National Accounts Statistics (GDP), Wholesale Price Index and Environmental Statistics — and the source code is published on GitHub under an MIT licence.

Independent testing found that figures returned by the server matched official press releases and bulletins. Known limitations include difficulty handling large data subsets and a lack of automatic warnings about base-year revisions or series discontinuities, making the tool better suited to headline lookups than deep time-series analysis.