Development Indicators MCP server

Development Indicators MCP

A provenance-first Model Context Protocol gateway for official international-development indicators.

Hosted MCP endpoint: https://indicatorsmcp.impactengines.ai/mcp

The project aims to let AI agents discover and query authoritative indicators across institutions such as the World Bank, UN agencies, FAO, WHO, UNICEF, ILO and the DHS Program through one consistent interface. It preserves definitions, units, dimensions, source codes and citations rather than returning uncited prose.

Current milestone

The repository contains a working vertical slice:

UNESCO UIS, OECD and ADB adapters;

• remote-capable MCP server using Streamable HTTP, with stdio support for local clients;
• source registry describing APIs, authentication and capabilities;
• normalized indicator and observation schemas;
• live World Bank, WHO GHO, UNICEF, FAOSTAT, ILOSTAT, IMF, UNSD SDG,

bounded provider waits and a 15-minute query cache;

• on-demand FAOSTAT authentication with no background token refresh;
• dynamic FAOSTAT domain, country, item and element discovery;
• weighted live catalogue search with aliases, match explanations, retrieval-health signals,

• partial-failure comparisons, typed errors, native structured outputs and compact responses;
• partial-success geography resolution with structured unresolved-country errors;
• normalized ILOSTAT frequency labels and FAOSTAT dimension-ranking evidence;
• tools to resolve country names, inspect metadata and retrieve observations;
• unit tests for normalization and source behaviour.

This is a public beta, not a production statistical service. The hosted instance is provided for evaluation; you can also run or deploy your own copy.

MCP tools

• list_sources(topic=None)
• getsourcesetup(source_id)
• searchindicators(query, sourceids=None, limit=10)
• getindicatormetadata(series_ref)
• getobservations(seriesref, countrycodes, startyear=None, endyear=None, latestonly=False, include_original=False)
• compareobservations(seriesrefs, country_codes, ...)
• find_microdata(query, country=None)
• faostatlistdomains(limit=50, cursor=0, groupcode=None, status=None, includearchived=False)
• faostatsearchdimension(dataset, dimension, query, limit=20, cursor=0)
• resolvegeographies(namesor_codes)

Series references use the form sourceid:seriescode, for example worldbank:SP.POP.TOTL. Observation calls accept ISO 3166-1 alpha-3 codes such as GHA and KEN; use resolvegeographies when a prompt supplies country names. Mixed batches return both resolved and unresolved entries instead of failing the entire request.

Local development

py -3.11 -m venv .venv
.venv\Scripts\Activate.ps1
pip install -e ".[dev]"
pytest
development-data-mcp

For macOS or Linux, activate the environment with source .venv/bin/activate.

Run the live-source smoke benchmark with:

python -m benchmarks.run

The FAOSTAT check is skipped until FAOSTATUSER and FAOSTATPASSWORD are configured; all public-source checks run without credentials.

The default transport is stdio. To run a hosted-style HTTP endpoint:

$env:MCP_TRANSPORT = "streamable-http"
$env:MCP_HOST = "127.0.0.1"
$env:MCP_PORT = "8000"
development-data-mcp

The MCP endpoint is then exposed at /mcp. Production deployment must add HTTPS, authentication, rate limiting and audit logging at the application or gateway layer.

Install in Codex

The hosted service uses Streamable HTTP:

codex mcp add development-indicators --url https://indicatorsmcp.impactengines.ai/mcp
codex mcp list

Shortened. The full README is on GitHub.