UNICEF Stats MCP
PYPI · UNICEFSTATS-MCP · SCANNED SEP 21
UNICEF child development statistics: 790+ indicators, 200+ countries, SDMX-sourced. No API key.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 2 of 26 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 105 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability76
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3670 tokens (~244/item across 15 items; 9 tools + 6 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the UNICEF Stats MCP server?
UNICEF Stats MCP runs locally as a PyPI package, launched with uvx unicefstats-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · unicefstats-mcp
claude mcp add jpazvd-unicefstats-mcp -- uvx unicefstats-mcp
{
"mcpServers": {
"jpazvd-unicefstats-mcp": {
"command": "uvx",
"args": [
"unicefstats-mcp"
]
}
}
} {
"servers": {
"jpazvd-unicefstats-mcp": {
"command": "uvx",
"args": [
"unicefstats-mcp"
]
}
}
} codex mcp add jpazvd-unicefstats-mcp -- uvx unicefstats-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"jpazvd-unicefstats-mcp": {
"type": "local",
"command": [
"uvx",
"unicefstats-mcp"
],
"enabled": true
}
}
} openclaw mcp add jpazvd-unicefstats-mcp --command uvx --arg unicefstats-mcp
mcp_servers:
jpazvd-unicefstats-mcp:
command: "uvx"
args: ["unicefstats-mcp"] {
"McpServers": {
"jpazvd-unicefstats-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"unicefstats-mcp"
]
}
}
} assistant mcp add jpazvd-unicefstats-mcp -t stdio -c uvx -a unicefstats-mcp
{
"mcpServers": {
"jpazvd-unicefstats-mcp": {
"command": "uvx",
"args": [
"unicefstats-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Sept 26 −3
- Stability: pass → 0.83 functional
- 19 Sept 26 +1
- Stability: 0.97 → pass security
- 17 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 16 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 15 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 14 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Sept 2026 · Analysed pypi/unicefstats-mcp@1.5.5
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 26 packages
| Packages resolved | 26 |
|---|---|
| Stale | 2 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
get_api_reference Get unicefdata API Reference (Python / R / Stata) ~175
Get the unicefdata package API reference for Python, R, or Stata. Returns function signatures, parameter descriptions, and usage examples. Use this when you need to write code that uses the unicefdata package, or when the user wants to move from conversational exploration to reproducible scripts.
| Name | Type | Req | Description |
|---|---|---|---|
| function | – | – | Optional function name to filter the reference to a single entry (e.g. 'unicefData', 'list_indicators'). If omitted, returns the full reference. |
| language | string | – | Target language for the unicefdata code template. One of 'python', 'r', or 'stata' (case-insensitive — the server normalises before lookup). Returns the language-specific API surface for users who wa… |
Structured output declared, but exposes no named fields.
No examples provided.
get_data Fetch UNICEF Indicator Data ~1,842
Fetch UNICEF data for an indicator and one or more countries. Returns annual observations from the UNICEF SDMX API. Use format="compact" (default) for a clean 5-column table; use format="full" for all columns including disaggregation details and confidence bounds. **`indicator` accepts BOTH codes AND human-readable names** (v0.7.0). Pass whichever you have from the user's question — the server resolves names to canonical codes for you. Examples: indicator='CME_MRM0' → code passthrough indicator='neonatal mortality' → resolves to 'CME_MRM0' indicator='Under-five mortality rate' → resolves to 'CME_MRY0T4' indicator='U5MR' → resolves to 'CME_MRY0T4' indicator='stunting' → resolves to 'NT_ANT_HAZ_NE2' indicator='LBW' / 'low birth weight' → resolves to 'NT_BW_LBW' Acronyms accepted: NMR, IMR, U5MR, SBR, LBW, ANC1, SAB, BCG, DTP1/3 … Genuinely ambiguous queries are refused with a disambiguation list. Examples: indicator='child mortality' → refused: pick CME_MRM0 / CME_MRY0 / CME_MRY0T4 / CME_MRY1T4 indicator='vaccination' → refused: pick IM_BCG / IM_DTP1/3 / IM_MCV1/2 **Prefer passing the user's phrasing verbatim over guessing the code from memory** — that's where the v0.6.x had a documented failure mode (model recalls `CME_MRY0T4` thinking it's neonatal mortality; it's under-five). The response echoes the resolution under `indicator_resolution` so you can confirm the canonical code+name match the user's intent. **`countries` accepts BOTH ISO3 codes AND country names** (v0.6.2). Pass whichever you have from the user's question — the server resolves country names to canonical ISO3 codes for you. Examples: countries=['Burundi'] → resolves to ['BDI'] countries=['BDI', 'Belgium'] → resolves to ['BDI', 'BEL'] countries=['Cote d\'Ivoire'] → resolves to ['CIV'] countries=['USA', 'UK'] → reso…
| Name | Type | Req | Description |
|---|---|---|---|
| age | – | – | SDMX age slice (e.g. 'Y15T19' for 15-19 years). Routed through raw=True + post-filter — engages mode='raw_filtered'. |
| cascade_on_empty | boolean | – | Opt into upstream `unicefdata`'s multi-dataflow cascade. When True AND the indicator has ≥2 dataflows in metadata AND a year or country filter is set, an empty primary-dataflow response causes upstre… |
| countries | array | yes | List of ISO3 country codes (e.g. ['BRA', 'IND', 'NGA']) OR country names (e.g. ['Brazil', 'India']). Names are resolved server-side. Hard cap of 30 entries per request. |
| end_year | – | – | Inclusive end year (e.g. 2023). Refused if > frontier. |
| filters | – | – | Free-form filter dict for any dim not first-class via unicefData() — WEALTH_QUINTILE, RESIDENCE, EDUCATION_LEVEL, DISABILITY_STATUS, etc. Engages mode='raw_filtered'. Use get_indicator_info to discov… |
| format | string | – | 'compact' = 5-column table (default); 'full' = all SDMX columns including disaggregation details and confidence bounds. |
| indicator | string | yes | UNICEF SDMX indicator code (e.g. 'CME_MRY0T4') OR human-readable name (e.g. 'under-5 mortality'). Names are resolved server-side. |
| limit | integer | – | Maximum row count. Carries `truncated: true` in envelope if hit. |
| residence | – | – | REMOVED in v1.2.0. Use filters={'RESIDENCE': 'U'}. |
| sex | string | – | SDMX sex code: '_T' (total, default), 'F' (female), 'M' (male). First-class via the unicefData() call. |
| start_year | – | – | Inclusive start year (e.g. 2010). Refused if > frontier. |
| wealth_quintile | – | – | REMOVED in v1.2.0. Use filters={'WEALTH_QUINTILE': 'Q1'}. |
Structured output declared, but exposes no named fields.
No examples provided.
get_indicator_info Get UNICEF Indicator Metadata ~123
Get full metadata for a UNICEF indicator. Returns description, category, dataflow, and SDMX API details. Use this before calling get_data() to understand what the indicator measures and which disaggregation filters (sex, age, wealth_quintile, residence) apply.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | Exact UNICEF SDMX indicator code (e.g. 'CME_MRY0T4' for under-5 mortality, 'NT_ANT_HAZ_NE2' for stunting). Case-sensitive. Use search_indicators if you don't already know the code. |
Structured output declared, but exposes no named fields.
No examples provided.
get_server_metadata Get unicefstats-mcp Server Metadata ~65
Return machine-readable identity, provenance, and version information for this MCP server. Use this to verify you are connected to the authentic unicefstats-mcp server and to inspect its canonical identity, data source, and publisher information. No API call — returns local metadata only.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
get_temporal_coverage Get UNICEF Indicator Temporal Coverage ~114
Check what years of data are available for a UNICEF indicator. Fetches a small sample to determine the time range. Lightweight — does not fetch all observations. Use before get_data() to pick a year range.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | Exact UNICEF SDMX indicator code. Returns the min/max observed year range (the 'data frontier') across all countries. The MCP uses this internally to refuse get_data calls whose year(s) exceed the fr… |
Structured output declared, but exposes no named fields.
No examples provided.
list_categories List UNICEF Indicator Categories ~132
List all UNICEF indicator categories (thematic groups). Categories correspond to SDMX dataflows: CME (child mortality), NUTRITION, EDUCATION, CHILD_PROTECTION, WASH, HIV_AIDS, etc. Use this to browse available topics before searching for specific indicators.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of categories to return per page. |
| offset | integer | – | Pagination offset — skip this many categories before returning. The envelope carries `has_more` and `next_offset` so the LLM can page through. UNICEF has ~25-40 categories so a single page is almost… |
Structured output declared, but exposes no named fields.
No examples provided.
list_countries List UNICEF Country Codes ~159
List countries available in the UNICEF database with ISO3 codes. Optionally filter by region name (case-insensitive partial match). Use the iso3 values in get_data().
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of countries to return per page. |
| offset | integer | – | Pagination offset — skip this many countries before returning. Use with `limit` to page through. UNICEF's country list has ~450 entries (member states + dependent territories + regional aggregates),… |
| region | – | – | Optional region filter applied as a case-insensitive substring match against each country's name (e.g. 'asia' matches 'South Asia'). Not a UNICEF region code lookup. When omitted, returns all 200+ co… |
Structured output declared, but exposes no named fields.
No examples provided.
lookup_by_code Lookup UNICEF Indicator by Exact Code ~349
Strict canonical lookup of a UNICEF indicator by its exact code. Use this INSTEAD of search_indicators when you already have a UNICEF indicator code (e.g. CME_MRY0T4, IM_DTP3, ED_15-24_LR). Do NOT pass natural-language descriptions, synonyms, or partial names — this tool is canonical-only. Two-tool separation introduced in v0.9.0 to give the LLM a self-describing choice at tool-selection time: - have a CODE? → lookup_by_code(code) - have WORDS? → search_indicators(query) Returns the same canonical metadata shape as get_indicator_info on success. On unknown code, returns an error with an explicit abstain_instruction directing the model to stop — NOT to fall back to search_indicators (which would re-enter the loop that 96% of v9 Arm B stuck queries hit). Returns: - on success: {status: "ok", code, name, description, dataflow, sdmx_api, disaggregation_filters, ambiguity_flag: false, ...} - on unknown code: {status: "error", error, ambiguity_flag: false, abstain_instruction, tip} - on natural-language input mistakenly passed: {status: "error", error, abstain_instruction directing to search_indicators}
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | Exact UNICEF SDMX indicator code (e.g. 'CME_MRY0T4'). Same envelope as get_indicator_info — both route through a shared _build_indicator_envelope helper, so the disaggregation_filters block is litera… |
Structured output declared, but exposes no named fields.
No examples provided.
search_indicators Search UNICEF Indicators ~352
Search UNICEF child development indicators by keyword. Returns indicator codes, names, and categories. Use the returned `code` values with get_indicator_info() or get_data(). Always start here if you don't know the indicator code. Examples: "mortality", "breastfeeding", "education", "child labour", "stunting" v1.1.0 advisory layer (additive to v0.9.0/v1.0.0 ambiguity_flag): - If response carries requires_confirmation=True, STOP and ask the user to disambiguate before calling get_data. - If response carries recommended + next_step, the model SHOULD call next_step verbatim (e.g. get_indicator_info(code='...')). - assistant_guidance is a plain-English directive (<200 chars). - Decision order: curated-ambiguous -> curated-preferred -> confident match -> none (wire-equivalent to v1.0.0). See internal/v1.1.0_design/ for rationale.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of indicator candidates to return. |
| offset | integer | – | Pagination offset — skip this many top-ranked matches before returning. Use with `limit` to page through long match lists (e.g. limit=20, offset=0 for page 1; offset=20 for page 2). The response enve… |
| query | string | yes | Natural-language search query (e.g. 'under-5 mortality', 'stunting', 'IMR', 'modelled estimates'). Accepts acronyms, common synonyms, and methodology phrases. |
Structured output declared, but exposes no named fields.
No examples provided.
What is the UNICEF Stats MCP server?
UNICEF Stats MCP is listed in the public MCP registry as io.github.jpazvd/unicefstats-mcp. UNICEF child development statistics: 790+ indicators, 200+ countries, SDMX-sourced. No API key. This page covers its PyPI package (unicefstats-mcp).
Is the UNICEF Stats MCP server safe to use?
UNICEF Stats MCP scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the UNICEF Stats MCP server expose?
UNICEF Stats MCP exposes 9 tools: search_indicators, list_categories, list_countries, get_indicator_info, lookup_by_code, and 4 more. Their descriptions and schemas cost roughly 3,311 tokens of context every time the server is loaded.
Is the UNICEF Stats MCP server still maintained?
UNICEF Stats MCP is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.