Skip to main content
Glama
global-education-mcp

global-education-mcp

by malkreide

πŸ‡¨πŸ‡­ Part of the Swiss Public Data MCP Portfolio

πŸŽ“ global-education-mcp

Version License: MIT Python 3.11+ MCP Data: UNESCO UIS Data: OECD Tests No API Key CI

MCP server for international education data – UNESCO UIS (4,000+ indicators across all member countries) and OECD Education at a Glance via SDMX. No API keys required.

πŸ‡©πŸ‡ͺ Deutsche Version

global-education-mcp demo flow


Overview

global-education-mcp gives AI assistants like Claude a complete international education intelligence system – literacy rates, enrolment ratios, education expenditure, teacher salaries, gender parity and SDG-4 monitoring, all accessible through a single standardised MCP interface.

The server bridges two of the most authoritative sources for internationally comparable education statistics: UNESCO UIS (global coverage, 4,000+ indicators) and the OECD's annual Education at a Glance (38 OECD countries, SDMX REST API). Both are open and require no API key.

Anchor demo query: "Compare Switzerland's education expenditure as a percentage of GDP with Finland, Singapore and South Korea over the last 10 years – and flag any SDG-4 gaps."


Related MCP server: unesco-mcp

Features

  • 🌍 UNESCO UIS – 4,000+ indicators, all UNESCO member countries, no API key

  • πŸ“Š OECD Education at a Glance – 38 OECD countries + partners via SDMX REST

  • πŸ” Indicator search – browse and filter the full UNESCO indicator catalogue

  • πŸ—ΊοΈ Multi-country comparison – benchmark any indicator across multiple countries

  • 🏫 Country education profiles – 10 core indicators in one call

  • 🎯 SDG-4 monitoring – structured reporting on Education for All targets

  • πŸ“ˆ OECD dataset search – discover and retrieve Education at a Glance dataflows

  • πŸ”‘ No API keys required – fully open data, zero setup friction

  • ☁️ Dual transport – stdio for Claude Desktop, Streamable HTTP (/mcp, spec 2026-07-28) for cloud deployment

  • πŸ›‘οΈ Graceful degradation – API failures return helpful messages with local reference fallback


Prerequisites

  • Python 3.11+

  • uv (recommended) or pip

  • No API keys needed


Installation

# Clone the repository
git clone https://github.com/malkreide/global-education-mcp.git
cd global-education-mcp

# Install
pip install -e ".[dev]"

Or with uvx (no permanent installation):

uvx global-education-mcp

Quickstart

# Start the server (stdio mode for Claude Desktop)
global-education-mcp

Try it immediately in Claude Desktop:

"What is Switzerland's literacy rate compared to Finland and Singapore?" "Show me education expenditure as % of GDP for CHE, DEU and AUT over the last 10 years."


Configuration

Claude Desktop Configuration

Windows (%APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "global-education": {
      "command": "uvx",
      "args": ["global-education-mcp"]
    }
  }
}

macOS (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "global-education": {
      "command": "uvx",
      "args": ["global-education-mcp"]
    }
  }
}

A ready-to-use claude_desktop_config.json is included in the repository root.

Cloud Deployment (Streamable HTTP for browser access)

For use via claude.ai in the browser (e.g. on managed workstations without local software).

⚠️ Security note: Since v0.3, MCP_HOST defaults to 127.0.0.1. The HTTP transport must always run behind a reverse proxy that adds TLS, authentication, and rate-limiting. Never expose the raw port to the internet β€” MCP_HOST=0.0.0.0 is only safe inside an isolated container network.

Docker (recommended):

The repository ships a hardened multi-stage Dockerfile and a docker-compose.yml that applies read_only: true, cap_drop: [ALL], security_opt: [no-new-privileges:true], and runs as non-root user uid 10001. The compose file binds the port to 127.0.0.1 so a host-level reverse proxy is required for any external access.

docker compose up --build
# then point nginx/caddy at 127.0.0.1:8000/mcp with TLS + auth

Plain docker run (without compose):

docker build -t global-education-mcp .
docker run --rm \
  --read-only --cap-drop ALL --security-opt no-new-privileges \
  --tmpfs /tmp:size=16M,mode=1777 \
  -p 127.0.0.1:8000:8000 \
  global-education-mcp

Render.com:

  1. Push/fork the repository to GitHub

  2. On render.com: New Web Service β†’ connect GitHub repo

  3. Set environment variables in the Render dashboard:

    MCP_TRANSPORT=streamable-http
    MCP_HOST=0.0.0.0      # Render needs 0.0.0.0; their edge layer provides TLS + auth.
    PORT=8000
  4. In claude.ai under Settings β†’ MCP Servers, add: https://your-app.onrender.com/mcp

Migrating from SSE. Up to v0.3.5 the container defaulted to MCP_TRANSPORT=sse with the endpoint /sse. The default is now streamable-http at /mcp β€” the transport through which 2026-07-28 clients send their single-POST requests; SSE has been superseded since spec 2025-03-26 and never offered that path. Existing deployments either switch the client URL to /mcp or set MCP_TRANSPORT=sse explicitly; the server then logs a legacy_transport_warning on start. An unknown MCP_TRANSPORT value now aborts the start instead of silently falling back to stdio.

πŸ’‘ "stdio for the developer laptop, sandboxed Streamable HTTP container for the browser."


Available Tools

UNESCO UIS Tools

Tool

Description

uis_list_indicators

Search and list available indicators (4,000+)

uis_list_countries

List countries and regions with ISO codes

uis_get_education_data

Retrieve data for a specific indicator

uis_compare_countries

Multi-country comparison for one indicator

uis_country_education_profile

Full education profile (10 core indicators)

uis_list_versions

List available database versions

OECD Tools

Tool

Description

oecd_list_education_datasets

List Education at a Glance datasets

oecd_get_education_indicator

Retrieve OECD education data via SDMX

oecd_search_datasets

Search OECD dataflows by keyword

Cross-Source Tools

Tool

Description

education_benchmark_countries

Benchmark multiple countries across 5 focus themes (UNESCO UIS)

Resources & Prompts

Resources:

  • education://indicators/unesco – Quick reference for core UNESCO indicators

  • education://datasets/oecd – Quick reference for OECD Education at a Glance dataflows

Prompts:

  • bildungsvergleich_schweiz – Switzerland vs. Finland, Singapore, Japan

  • sdg4_monitoring – SDG-4 report for CH/DE/AT

Country Codes

ISO 3166-1 Alpha-3 standard:

Code

Country

Code

Country

CHE

Switzerland

FIN

Finland

DEU

Germany

SGP

Singapore

AUT

Austria

KOR

South Korea

FRA

France

JPN

Japan

SWE

Sweden

USA

United States

Example Use Cases

Query

Tool

"What is Switzerland's literacy rate vs. Finland and Singapore?"

uis_compare_countries

"Education expenditure as % of GDP for CHE, DEU, AUT over 10 years"

uis_get_education_data

"Create a full education profile for South Korea"

uis_country_education_profile

"Which OECD datasets cover teacher salaries?"

oecd_search_datasets

"Compare secondary graduation rates across 5 European countries"

education_benchmark_countries

"Create an SDG-4 monitoring report for Switzerland"

sdg4_monitoring (prompt)

β†’ More use cases by audience β†’


Architecture

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚   Claude / AI   │────▢│   Global Education MCP       │────▢│   UNESCO UIS API   β”‚
β”‚   (MCP Host)    │◀────│   (MCP Server)               │◀────│   uis.unesco.org   β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β”‚                              β”‚     β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                        β”‚  10 Tools Β· 2 Resources      β”‚
                        β”‚   Β· 2 Prompts                β”‚     β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                        β”‚  stdio | Streamable HTTP     │────▢│   OECD SDMX API    β”‚
                        β”‚                              │◀────│   sdmx.oecd.org    β”‚
                        β”‚  server.py                   β”‚     β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                        β”‚   + api_client.py            β”‚
                        β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Infrastructure Components

Component

Metaphor

Function

HTTPClient

Postal service

Handles all outbound HTTP requests, retries and timeouts

SimpleCache

Whiteboard

In-memory TTL cache for repeated queries

GracefulFallback

Safety net

Returns local reference data when APIs are unavailable

SDMXParser

Translator

Converts OECD SDMX/XML responses to clean JSON

Caching Strategy

Data Source

Cache TTL

Rationale

UNESCO UIS indicators

3600s

Catalogue is stable; updated annually

UNESCO UIS country data

1800s

Figures update yearly, not intraday

OECD dataset list

3600s

Education at a Glance is an annual publication

OECD indicator data

1800s

Same annual update cycle

Country/region list

86400s

ISO codes and country lists are highly stable


Project Structure

global-education-mcp/
β”œβ”€β”€ src/global_education_mcp/       # Main package
β”‚   β”œβ”€β”€ __init__.py                 # Package metadata, version
β”‚   β”œβ”€β”€ server.py                   # FastMCP server, 10 tools, 2 resources, 2 prompts
β”‚   └── api_client.py               # HTTP client, UNESCO UIS + OECD wrappers, formatters
β”œβ”€β”€ scripts/
β”‚   └── record_fixtures.py          # Records the fixtures from the live UIS API
β”œβ”€β”€ tests/
β”‚   β”œβ”€β”€ fixtures/                   # Recorded responses + PROVENANCE.md (source, date, SHA-256)
β”‚   β”œβ”€β”€ fixture_data.py             # Fixture loader – raises on a missing name
β”‚   β”œβ”€β”€ test_source_contract.py     # Contract vs. the recording + live tests
β”‚   β”œβ”€β”€ test_server.py              # 42 tests (basic / intermediate / advanced)
β”‚   └── test_extended_scenarios.py  # 74 tests across 8 categories
β”œβ”€β”€ claude_desktop_config.json      # Ready-to-use Claude Desktop config
β”œβ”€β”€ pyproject.toml                  # Build configuration (hatchling)
β”œβ”€β”€ CHANGELOG.md
β”œβ”€β”€ CONTRIBUTING.md                 # Contribution guide (English)
β”œβ”€β”€ CONTRIBUTING.de.md              # Contribution guide (German)
β”œβ”€β”€ SECURITY.md                     # Security policy (English)
β”œβ”€β”€ SECURITY.de.md                  # Security policy (German)
β”œβ”€β”€ LICENSE
β”œβ”€β”€ README.md                       # This file (English)
└── README.de.md                    # German version

Known Limitations

  • UNESCO UIS: Some indicators have sparse coverage for low-income countries or recent years

  • OECD SDMX: Occasional API timeouts on large multi-country, multi-year requests; reduce the year range if needed

  • OECD coverage: 38 OECD members + select partners – does not cover all UNESCO member states

  • Historical depth: UNESCO UIS data availability varies by indicator; not all series go back to 1970

  • Language: UNESCO UIS returns indicator labels in English only; OECD labels may vary by dataflow

  • No real-time data: Both sources publish annually – figures reflect the latest published edition, not live school statistics

  • Estimated values are labelled: UIS marks part of its observations UIS_EST (UIS estimate) or NAT_EST (national estimate) – for LR.AG15T99 that is 1,306 of 9,818 values. The status column names it; an unlabelled value is a reported one.

  • Data rows carry the ISO code, not the country name: plain names come from uis_list_countries. The data tools print the code rather than inventing a name.

  • An unknown country code is not an error status: UIS answers HTTP 200 with an empty result set and states the reason in the payload's hints field. The tools print that hint – otherwise a typo would look exactly like a country without data.


Compliance & Data Classification (City of Zurich)

Verbindliche Klassifikation fΓΌr den Einsatz im Schulamt der Stadt ZΓΌrich (German section follows in README.de.md).

ISDS Protection Class (Stadt ZΓΌrich Schutzbedarfsklassen)

Dimension

Class

Reasoning

Confidentiality

public

UNESCO UIS data licensed under CC BY-SA 3.0 IGO; OECD EaG under public OECD Terms

Integrity

normal

Upstream is authoritative; local in-memory cache is TTL-bounded and never written to disk

Availability

normal

Graceful fallback to bundled static reference data when an API is unreachable

Overall protection class

G1 β€” public (ΓΆffentlich)

lowest tier per ISDS Stadt ZΓΌrich

  • Data owner: UNESCO UIS / OECD (external)

  • System owner: Schulamt der Stadt ZΓΌrich

  • Processes personal data: no

  • DSG / EDΓ–B relevance: none (only anonymized country-level aggregates)

Schulamt Classification (BUI / Vertraulich / Streng Vertraulich)

Aspect

Classification

Tool output (Markdown tables, summaries)

BUI (betrieblich unkritische Information)

In-memory TTL cache

BUI (same tier as source)

Structured logs (JSON on stderr, see OBS-003)

BUI β€” only tool name, params, duration; no PII

tools.lock.json, audits/ artefacts

BUI

β†’ The server is approved for any Schulamt use case without additional clearance from the data protection officer.

Compatibility

Component

Supported version

MCP Protocol

2024-11-05

MCP Python SDK

>=1.0.0,<2.0.0

Python

3.11, 3.12, 3.13

httpx

>=0.27.0,<1.0.0

pydantic

>=2.0.0,<3.0.0

Major-version upgrades are deliberate decisions β€” the upper bounds in pyproject.toml exist so a transitive bump does not silently break the server. See CHANGELOG.md for the upgrade trail.


πŸ›‘οΈ Safety & Limits

Aspect

Details

Access

Read-only (readOnlyHint: true) β€” the server cannot modify, write or delete any data

Personal data

No personal data β€” UNESCO UIS and OECD EaG publish only aggregated, country-level statistics

Rate limits

Built-in per-query caps (max 50 indicators per search, max 10 countries per comparison, conservative year ranges)

Caching

In-memory TTL cache (1800–86400s) reduces upstream load and respects publisher capacity

Timeout

30 seconds per upstream API call, with graceful fallback to local reference data

Authentication

No API keys required β€” both UNESCO UIS and OECD SDMX are publicly accessible

Licenses

UNESCO UIS data under CC BY-SA 3.0 IGO; OECD data under OECD Terms and Conditions

Terms of Service

Subject to ToS of the respective sources: UNESCO UIS, OECD β€” please cite the source when redistributing

Attribution

All tool responses include source attribution (Source: UNESCO UIS / Source: OECD Education at a Glance)


MCP Protocol Version

This server speaks two protocol eras over the same endpoint. The client's first request on a connection decides which one applies; a later claim from the other era is refused.

Era

Revision

Who reaches it

initialize handshake

2024-11-05 … 2025-11-25

What today's clients speak. The server answers with the revision asked for, or with the 2025-11-25 ceiling when the request asks for something newer.

Per-request envelope

2026-07-28

A request carrying the 2026-07-28 _meta envelope opens a modern connection.

Over HTTP both eras share the endpoint /mcp (MCP_TRANSPORT=streamable-http, stateless): a request with the MCP-Protocol-Version: 2026-07-28 header is served as a self-contained single exchange β€” no initialize, no Mcp-Session-Id. The legacy SSE transport (MCP_TRANSPORT=sse) offers no such path and reaches the handshake era only.

Both revisions are pinned in tests/test_protocol_version.py and asserted against the installed SDK, so a Dependabot bump of mcp cannot move either one silently. tests/test_streamable_http.py measures them: it builds the HTTP app with the options main() starts, and sends a 2026-07-28 client, an auto client, a legacy initialize and a raw server/discover through it. The CI Docker job sends the same server/discover to the hardened container.

What 2026-07-28 changes for this server. The logging capability is deprecated (SEP-2577) and is not used: announcements before a fan-out travel as progress 0 of n, operational logs go to stderr as JSON. serverInfo, which now rides in _meta on every response, carries the package version. List methods carry freshness hints (ttlMs, cacheScope, SEP-2549).

Note that the SDK's LATEST_PROTOCOL_VERSION is an alias for the modern era, not for the handshake era β€” pinning against it alone would leave the era that current clients actually negotiate free to drift.

Update policy. When the gate fails, do not edit the constant blindly: read the spec changelog between the two revisions, verify the server still behaves, then move the constant, this section, README.de.md and CHANGELOG.md together.


Testing

# Unit tests (no API key required, no network)
PYTHONPATH=src pytest tests/ -v -m "not integration"

# Full suite including the live tests against api.uis.unesco.org
PYTHONPATH=src pytest tests/ -v

# Re-record the fixtures (writes tests/fixtures/ + PROVENANCE.md)
PYTHONPATH=src python scripts/record_fixtures.py

169 tests – 152 offline, 17 against the live source.

Category

Tests

Description

Edge cases & boundary values

19

Year limits, string lengths, null/zero values

Security & adversarial inputs

14

Injection attempts, HTTP error codes, whitespace

Output quality

11

Markdown structure, source attribution, sort order

Resilience & error cascades

9

Full API outage, partial results, timeouts

Subject-matter correctness

10

SDG-4 coverage, correct indicators per focus theme

Performance & concurrency

4

Concurrent requests, time limits

Schulamt scenarios

7

DACH comparison, PISA, teacher shortage

Source contract vs. the recording

23

Field names, envelope, query parameters, hints

Live tests (-m integration)

17

The paths, the shape, and the tools themselves

Why the fixtures are recorded rather than written

A hand-written mock encodes its author's assumption and therefore cannot refute it: production code and fixture come from the same head, the same hour, the same reading of the docs. Where both are wrong, both are wrong together β€” and the suite stays green.

That is not a hypothetical here. Before 2026-08-08 this repo had 128 green tests while three of its four UNESCO paths answered HTTP 404 and every data query returned an empty list. The mocks carried the same invented field names as the production code (observations, indicatorId, entityType), so nothing could ever contradict them.

Every fixture under tests/fixtures/ is now a recorded response. PROVENANCE.md names the source URL, the recording date, the selection rule and the SHA-256 for each one. Without a date, "recorded" becomes indistinguishable from "invented" after two years β€” the file looks the same.

Three of the fixtures are controls: a made-up theme value, a made-up country code, and the same time series requested twice with different parameter names. Without them a measurement only shows what we received; with them it shows what the source actually distinguishes.


Contributing

Contributions are welcome. Please open an issue first to discuss what you would like to change.

  • Follow the existing code style (Ruff linting, Black formatting)

  • Add tests for new tools (tests/test_server.py or test_extended_scenarios.py)

  • Use the @pytest.mark.integration marker for tests that call live APIs

  • Update CHANGELOG.md and the tool table in this README

  • See CONTRIBUTING.md for the full contribution guide


Changelog

See CHANGELOG.md


Security

To report a vulnerability, see SECURITY.md (πŸ‡©πŸ‡ͺ Deutsche Version). Please use the private channels described there rather than public issues.


License

MIT License β€” see LICENSE


Author

Hayal Oezkan Β· github.com/malkreide


MCP Client Configuration

Run via uv's uvx β€” no clone or manual install needed. Add to your MCP client config (mcpServers for Claude Desktop, Cursor and Windsurf; use a top-level servers key for VS Code in .vscode/mcp.json):

{
  "mcpServers": {
    "global-education-mcp": {
      "command": "uvx",
      "args": [
        "global-education-mcp"
      ]
    }
  }
}

Available Tools

10 tools
education_benchmark_countriesA
Read-only

Benchmarkt mehrere LΓ€nder auf einem Bildungsthema via UNESCO UIS.

Automatisch werden die passenden Indikatoren fΓΌr den gewΓ€hlten Fokus ausgewΓ€hlt und ein strukturierter Vergleich erstellt.

Fokus-Optionen:

  • literacy: Alphabetisierungsraten (Erwachsene + Jugendliche)

  • spending: Bildungsausgaben (% BIP, verschiedene Stufen)

  • completion: Abschlussquoten (Primar, Sek I, Sek II)

  • teachers: SchΓΌler-Lehrer-VerhΓ€ltnis + Lehrerausbildung

  • enrollment: Einschulungsraten nach Schulstufe

Args: params: country_codes, focus

Returns: VollstΓ€ndiger Benchmarkreport mit Tabellen fΓΌr alle relevanten Indikatoren

Inputs: params (required). Returns: result

oecd_get_education_indicatorB
Read-onlyIdempotent

Ruft Bildungsdaten aus dem OECD Education at a Glance Report ab.

Greift auf die OECD SDMX REST API zu. Liefert strukturierte Daten fΓΌr OECD-LΓ€nder zu Bildungsausgaben, Einschreibungsraten, LehrergehΓ€ltern etc.

Beispiele:

  • Bildungsausgaben Schweiz/DE/AT: dataflow='EAG_FISC', countries=['CHE','DEU','AUT']

  • LehrergehΓ€lter OECD: dataflow='EAG_PERS_SALARY'

  • BeschΓ€ftigung nach Bildungsabschluss: dataflow='EAG_EMP_EDUC'

Args: params: dataflow_id, countries (optional), start_period, end_period

Returns: Markdown-formatierte Datentabelle oder Rohdaten-Zusammenfassung

Inputs: params (required). Returns: result

oecd_list_education_datasetsA
Read-onlyIdempotent

Listet verfΓΌgbare OECD Education at a Glance DatensΓ€tze auf.

Education at a Glance ist das jΓ€hrliche Referenzwerk der OECD fΓΌr internationale Bildungsvergleiche. Es umfasst 38 OECD-LΓ€nder plus Partner.

Abgedeckte Themenbereiche:

  • Bildungsbeteiligung und -abschlΓΌsse (EAG_ENRL, EAG_GRAD_ENTR)

  • Bildungsausgaben und Finanzierung (EAG_FISC)

  • Lehrpersonal und Arbeitsbedingungen (EAG_PERS, EAG_PERS_SALARY)

  • Bildungsrendite und Arbeitsmarkt (EAG_EMP_EDUC, EAG_EARN_RATIO)

Returns: Markdown-Liste der DatensΓ€tze mit Beschreibungen und Dataflow-IDs

Inputs: no named parameters. Returns: result

oecd_search_datasetsA
Read-onlyIdempotent

Durchsucht alle OECD-DatensΓ€tze nach einem Stichwort.

Über die OECD SDMX API sind hunderte DatensÀtze verfügbar. Diese Funktion findet DatensÀtze mit Bildungsbezug oder anderen Themen.

Args: params: keyword, limit

Returns: Markdown-Liste gefundener DatensΓ€tze mit Dataflow-IDs

Inputs: params (required). Returns: result

uis_compare_countriesA
Read-onlyIdempotent

Vergleicht Bildungsindikatoren zwischen mehreren LΓ€ndern (UNESCO UIS).

Ideal fΓΌr den direkten internationalen Vergleich: Wie steht die Schweiz im Vergleich zu Finnland, Singapur und dem OECD-Durchschnitt?

Args: params: indicator_id, country_codes (Liste), year (optional)

Returns: Markdown-Vergleichstabelle sortiert nach Indikatorwert

Inputs: params (required). Returns: result

uis_country_education_profileA
Read-onlyIdempotent

Erstellt ein umfassendes Bildungsprofil fΓΌr ein Land via UNESCO UIS.

Ruft automatisch die wichtigsten SchlΓΌsselindikatoren ab: Alphabetisierung, Einschulungsraten, Abschlussquoten, Bildungsausgaben, SchΓΌler-Lehrer-VerhΓ€ltnis, GeschlechterparitΓ€t.

Args: params: country_code (ISO Alpha-3), latest_year_only

Returns: VollstΓ€ndiges Markdown-Bildungsprofil mit allen Kernindikatoren

Inputs: params (required). Returns: result

uis_get_education_dataA
Read-onlyIdempotent

Ruft Bildungsdaten von der UNESCO Institute for Statistics API ab.

Kernfunktion des Servers. Liefert international vergleichbare Daten zu einem spezifischen Indikator – fΓΌr ein Land oder alle LΓ€nder.

Typische AnwendungsfΓ€lle:

  • Alphabetisierungsrate der Schweiz: indicator='LR.AG15T99', country='CHE'

  • Bildungsausgaben OECD-LΓ€nder: indicator='XGDP.FSGOV', kein Land

  • Schulabschlussquoten Europa: indicator='CR.1' + Jahresfilter

  • Bildungsausgaben-Zeitreihe: indicator='XGDP.FSGOV', country='CHE'

Ein unbekannter LΓ€ndercode ist hier keine Fehlermeldung: Die Quelle antwortet mit HTTP 200 und leerer Trefferliste, nennt den Grund aber in hints. Dieser Hinweis wird mit ausgegeben β€” sonst sΓ€he ein Tippfehler genauso aus wie ein Land ohne Daten.

Args: params: indicator_id (erforderlich), country_code, start_year, end_year

Returns: Markdown-formatierte Tabelle oder Zeitreihe mit Daten und Metadaten

Inputs: params (required). Returns: result

uis_list_countriesA
Read-onlyIdempotent

Listet verfΓΌgbare LΓ€nder und Regionen in der UNESCO UIS-Datenbank auf.

Gibt ISO 3166-1 Alpha-3 Codes zurΓΌck, die fΓΌr Datenabfragen benΓΆtigt werden. Beispiele: CHE (Schweiz), DEU (Deutschland), AUT (Γ–sterreich), FRA (Frankreich).

Neben EinzellΓ€ndern (NATIONAL) sind regionale Aggregate (REGIONAL) verfΓΌgbar: Weltregionen, Einkommensgruppen, SDG-Regionen.

Args: params: search (optional Textfilter), entity_type (optional)

Returns: Markdown-Liste mit ISO-Codes und LΓ€ndernamen

Inputs: params (required). Returns: result

uis_list_indicatorsA
Read-onlyIdempotent

Listet verfΓΌgbare Indikatoren der UNESCO Institute for Statistics auf.

Die UIS bietet ΓΌber 4'000 Indikatoren zu Bildung, Wissenschaft, Kultur und Kommunikation. Diese Funktion dient zur Exploration und Indikatorsuche.

Wichtige Indikator-Kategorien (am 2026-08-08 gegen die Quelle gehalten; NERA.*, XUNIT.* und PTR.* standen hier, existieren dort aber nicht):

  • Alphabetisierung (LR.*): Lese-/Schreibkompetenz nach Alter, Geschlecht

  • Einschulungsraten (NERT., OFST.): Netto-Einschulung, Kinder ausserhalb der Schule

  • SchulabschlΓΌsse (CR.*): Abschlussquoten Primar- bis Sekundarstufe

  • Bildungsausgaben (XGDP.*): % BIP

  • Lehrpersonen (TRTP., FTP.): Mindestqualifikation, Frauenanteil

Args: params: theme (optional), search (optional), limit

Returns: Markdown-Liste mit Indikator-IDs und Beschreibungen

Inputs: params (required). Returns: result

uis_list_versionsA
Read-onlyIdempotent

Listet verfΓΌgbare Versionen der UNESCO UIS-Datenbank auf.

Die UIS verΓΆffentlicht mehrmals jΓ€hrlich neue Datenversionen. NΓΌtzlich um sicherzustellen, dass mit den neuesten Daten gearbeitet wird.

Returns: Markdown-Liste mit Versionsbezeichnungen und Publikationsdaten

Inputs: no named parameters. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 10 tools

    Disambiguation4/5

    The four data-retrieval tools (uis_get_education_data, uis_compare_countries, education_benchmark_countries, uis_country_education_profile) have distinguishable scopes (raw single-indicator vs multi-country vs multi-indicator benchmark vs single-country profile), but compare_countries and benchmark_countries could still be confused by an agent. The OECD vs UIS source split is clear.

    Naming Consistency4/5

    Most tools follow a source_action pattern (uis_list_indicators, oecd_get_education_indicator, uis_compare_countries), which is largely predictable. However education_benchmark_countries breaks the prefix convention and the action phrasing varies (get vs compare vs profile), creating minor inconsistency.

    Tool Count5/5

    Ten tools is well-scoped for a dual-source (UIS + OECD) education data server, covering discovery, retrieval, comparison, and profiling without redundancy. Each tool earns its place.

    Completeness4/5

    The surface covers indicator/dataset discovery, country listing, raw data retrieval, comparison, benchmarking, and country profiles across both UIS and OECD. Minor gaps exist (no indicator metadata lookup, no version selection passed to queries), but core workflows are complete.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A Model Context Protocol server that connects AI assistants to UNESCO Institute for Statistics data, enabling natural language search, retrieval, and comparison of indicators across countries.
      13
      3
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to discover, retrieve, and compare official international development indicators from sources such as the World Bank, FAOSTAT, WHO, UNICEF, and IMF, while preserving source identifiers, units, and citations.
      10
      2
      MIT