unicefstats-mcp

Experimental — not an official UNICEF product. Verify retrieved values against the UNICEF Data Warehouse before citing in publications. See Limitations.

MCP server for UNICEF child development statistics. Query 790+ child-focused indicators across 200+ countries with disaggregations by sex, age, wealth quintile, and residence. No API key required.

Indicators cover child mortality, nutrition, education, child protection, WASH (water/sanitation/hygiene), HIV/AIDS, immunization, early childhood development, and more. Many align with SDG targets, but the dataset is broader than SDGs alone.

Data source: UNICEF SDMX API

Identity

Property	Value
MCP identity	io.github.jpazvd/unicefstats-mcp
PyPI package	unicefstats-mcp
Canonical source	github.com/jpazvd/unicefstats-mcp
Data source	UNICEF Data Warehouse via SDMX REST API
Maintainer	Joao Pedro Azevedo (jpazvd)
Status	Experimental — not endorsed by UNICEF

Third-party aggregator listings (LobeHub, Smithery, mcp.so, Glama) are not controlled by the maintainer. Verify against the canonical source above.

Contents

• How it relates to the unicefdata packages
• How it compares to other data MCPs
• Landscape: MCP servers for official statistics
• Relationship to sdmx-mcp
• Quick Start
• Tools
• Demo
• Prompts
• Benchmark Results
• Deployment
• Development
• Contributing
• Limitations and Hallucination Risks
• Provenance and Ownership
• How to Verify This MCP
• License

Key documents

Document	Description
PROVENANCE.md	Data origin, ownership, distribution pipeline, verification steps
CHANGELOG.md	Version history (v0.1.0–v0.4.0) with sources cited
RELEASE.md	Release process checklist and version management
CONTRIBUTING.md	Development setup, code style, PR guidelines
CODE_OF_CONDUCT.md	Contributor Covenant v2.1
examples/RESULTS.md	Full 300-query benchmark analysis with EQA decomposition
examples/LITERATURE_REVIEW.md	Literature review: MCP servers for official statistics — ecosystem, patterns, evaluation, 15 papers
examples/LANDSCAPE.md	20 official statistics MCP servers compared — timeline, feature matrix, strengths/weaknesses
examples/results/related_work.md	Annotated bibliography — 15 papers on tool-augmented hallucination
examples/results/statistical_summary.md	Wilcoxon, bootstrap CI, McNemar tests on benchmark results
examples/MCP-DIRECTORY-STATS.md	Comprehensive directory of all official statistics MCP servers
examples/mcp-smoke-test/MULTIMODEL_SMOKETEST.md	Cross-model smoke test (Anthropic / OpenAI / Google / OpenRouter) for the v0.7.3 cross-provider generalisation question — design, rubric, ~$1 default run, path to full mini-EQA

How it relates to the unicefdata packages

unicefstats-mcp is not a replacement for the unicefdata packages in Python, R, or Stata. They serve different audiences:

	unicefstats-mcp	unicefdata (Python/R/Stata)
Audience	AI assistants (Claude, Cursor, Copilot)	Data scientists, researchers, analysts
Interface	MCP protocol (tool calls via JSON)	Native language API (library(), import, ssc install)
Use case	Conversational data exploration, quick lookups, AI-assisted analysis	Reproducible research, ETL pipelines, statistical analysis
Output	JSON (compact or full) optimized for LLM context	DataFrames, tibbles, Stata matrices
Scripting	No — single queries via AI chat	Yes — full programmatic control, loops, joins, transforms
Caching	Delegates to unicefdata	Built-in SDMX response caching
Bulk download	Limited (max 500 rows per call)	Unlimited — designed for full dataset pulls

Under the hood, unicefstats-mcp wraps the unicefdata Python package. Every tool call ultimately calls unicefdata.unicefData() or its metadata functions. Think of the MCP as a thin AI-friendly interface on top of the same data layer.

When to use which:

• Use unicefstats-mcp when you're chatting with an AI and want to quickly explore indicators, check values, or compare countries
• Use unicefdata (Python/R/Stata) when you're writing scripts, building dashboards, running regressions, or doing any reproducible analytical work

How it compares to other data MCPs

Feature	unicefstats-mcp	FRED MCP	World Bank MCP
Tools	9 (search → metadata → data → code → identity + strict canonical lookup)	3 (browse → search → get)	1 (get only)
Indicators	790+ child-focused indicators	800,000+ economic series	~1,600 indicators
Countries	200+ (ISO3)	US-focused (some intl)	200+ (ISO2)
Disaggregations	Sex, age, wealth quintile, residence	Frequency, seasonal adjustment	None
MCP Prompt	compare_indicators	None	None
Output modes	Compact (5 cols) / Full (all cols)	JSON	CSV
Data summary	Value range, year range, country count	None	None
Pagination metadata	total_rows_available vs rows_returned	limit/offset	None (hardcoded 20K)
Input validation	ISO3, sex, wealth, residence validated	Zod schemas	None
Error guidance	error + tip with next steps	HTTP status text	Raw exception
API key	Not required	FRED_API_KEY required	Not required
Truncation handling	rows_truncated flag + filter tips	None	None

Landscape: MCP servers for official statistics

This project is part of a growing ecosystem of MCP servers for international and official statistics. As of March 2026:

UN Agencies

Server	Data Source	Tools	SDMX	Published
unicefstats-mcp (this repo)	UNICEF Data Warehouse	7	Yes	PyPI
sdmx-mcp	Any SDMX registry	23	Yes	No
unicef-datawarehouse-mcp	UNICEF Data Warehouse	3	Yes	No
mcp_unhcr	UNHCR refugee data	5	No	No
medical-mcp	WHO GHO / FDA / PubMed	18	No	npm

International Organizations

Server	Data Source	Tools	SDMX	Published
fred-mcp-server	FRED (800K+ series)	3	No	npm
world_bank_mcp_server	World Bank Open Data	1	No	No
imf-data-mcp	IMF (IFS, BOP, WEO)	10	Yes	PyPI
OECD-MCP	OECD (5,000+ datasets)	9	Yes	npm
eurostat-mcp	Eurostat EU statistics	7	Yes	No

National Statistics Offices

Server	Data Source	Tools	Published
us-census-bureau-data-api-mcp	US Census Bureau (official)	5	No
us-gov-open-data-mcp	40+ US Gov APIs	300+	npm
ibge-br-mcp	Brazil IBGE (227 tests)	22	npm
ukrainian-stats-mcp-server	Ukraine SDMX v3	8	npm
istat_mcp_server	Italy ISTAT SDMX	7	No

Known gaps