Development Indicators MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Development Indicators MCP Compare GDP per capita for Ghana, Kenya, and Nigeria from 2015 to 2023 using World Bank data."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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:
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, UNESCO UIS, OECD and ADB adapters;
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, bounded provider waits and a 15-minute query cache;
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.
Related MCP server: WHO MCP Server
MCP tools
list_sources(topic=None)get_source_setup(source_id)search_indicators(query, source_ids=None, limit=10)get_indicator_metadata(series_ref)get_observations(series_ref, country_codes, start_year=None, end_year=None, latest_only=False, include_original=False)compare_observations(series_refs, country_codes, ...)find_microdata(query, country=None)faostat_list_domains(limit=50, cursor=0, group_code=None, status=None, include_archived=False)faostat_search_dimension(dataset, dimension, query, limit=20, cursor=0)resolve_geographies(names_or_codes)
Series references use the form source_id:series_code, for example world_bank:SP.POP.TOTL.
Observation calls accept ISO 3166-1 alpha-3 codes such as GHA and KEN; use
resolve_geographies 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-mcpFor macOS or Linux, activate the environment with source .venv/bin/activate.
Run the live-source smoke benchmark with:
python -m benchmarks.runThe FAOSTAT check is skipped until FAOSTAT_USER and FAOSTAT_PASSWORD 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-mcpThe 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 listRestart Codex after adding it, then use /mcp to confirm the server and its
tools are available. The same MCP configuration is shared by the Codex CLI,
IDE extension and ChatGPT desktop app on the same Codex host.
Equivalent ~/.codex/config.toml configuration:
[mcp_servers.development-indicators]
url = "https://indicatorsmcp.impactengines.ai/mcp"
startup_timeout_sec = 30
tool_timeout_sec = 180Example test prompt: Using Development Indicators, find an official maize production series from FAOSTAT and retrieve 2020–2023 observations for Uganda and Kenya, preserving units, flags and citations.
Cloudflare deployment
The repository includes a Cloudflare Worker and Container configuration. It
routes public HTTPS requests to the same tested Python image; the MCP endpoint
remains /mcp. A production deployment should initially use its isolated
workers.dev hostname, then attach a custom domain after client verification.
npm install
npm run deployTo deploy under a different Worker name or hostname, edit name and routes in
wrangler.jsonc. Remove the routes block if you only want a workers.dev
endpoint. Authenticate Wrangler with your own Cloudflare account before running
the deploy command; the repository contains no Impact Engines credentials.
Optional provider credentials can be added to your Worker without committing them:
npx wrangler secret put FAOSTAT_USER
npx wrangler secret put FAOSTAT_PASSWORD
npx wrangler secret put UN_POPULATION_TOKENSee docs/deployment.md for the deployment architecture, verification checklist and non-Cloudflare Docker instructions.
Run with Docker
docker build -t development-data-mcp .
docker run --rm -p 8000:8000 \
-e MCP_TRANSPORT=streamable-http \
-e MCP_HOST=0.0.0.0 \
-e MCP_PORT=8000 \
development-data-mcpThe endpoint will be available at http://localhost:8000/mcp. Put it behind
HTTPS and suitable access controls before exposing it to the public internet.
Contributing
Issues and pull requests are welcome. Please run ruff check ., pytest, and
npm run typecheck before submitting a change. See CONTRIBUTING.md
for the full development workflow and SECURITY.md for private
vulnerability reporting guidance.
Cloudflare Containers require a Workers paid plan. FAOSTAT credentials, when configured, must be stored with Wrangler secrets rather than committed.
Architecture
AI client
|
Remote MCP gateway
|
Metadata registry and source router
|
Provider adapters (REST / SDMX / OData / specialist)
|
Official publisher APIsOnly metadata and modest request caches should be stored locally at first. Observations are retrieved from official sources and returned in a common envelope while preserving the original source identifiers.
Planned source sequence
Active observation connectors: World Bank Indicators, WHO GHO, UNICEF SDMX, FAOSTAT, ILOSTAT, IMF DataMapper, UNSD SDG, UNESCO UIS, OECD SDMX and ADB SDMX. UN Population indicator discovery is active; its observation endpoint requires a portal-issued bearer token. DHS, MICS, IPUMS and World Bank Microdata Library remain catalogue-discovery integrations rather than observation APIs.
Safety and statistical integrity
Values are never invented or inferred by the MCP.
Similar indicators are not silently merged.
Provider codes and canonical URLs are retained.
Observed, survey-estimated, modelled and projected values must be labelled when metadata permits.
Microdata catalogue discovery does not imply permission to download restricted files.
Large results should be exported rather than placed directly in model context.
License
The software is released under the MIT License. Upstream data remain subject to each publisher's terms, licences and attribution requirements.
Available Tools
10 toolscompare_observationsAInspect
Retrieve series side by side and flag obvious metadata differences without merging them.
Inputs: series_refs (required), country_codes (required), end_year, start_year, +2 more. Returns: series, source_errors, comparability_warnings
faostat_list_domainsCInspect
List live FAOSTAT groups and domains available to build source-qualified series.
Inputs: limit, cursor, status, group_code, +1 more. Returns: items, total, cursor, next_cursor
faostat_search_dimensionCInspect
Search a FAOSTAT domain's area, item, element, unit, or other definition table.
Inputs: query (required), dataset (required), dimension (required), limit, +1 more. Returns: items, total, cursor, next_cursor
find_microdataAInspect
Find relevant public microdata catalogues and state their access conditions.
Inputs: query (required), country. Returns: result
get_indicator_metadataBInspect
Retrieve authoritative metadata for a source-qualified series reference.
Inputs: series_ref (required). Returns: name, unit, topics, source_id, +8 more
get_observationsCInspect
Retrieve official observations while retaining metadata, citations and warnings.
Inputs: series_ref (required), country_codes (required), end_year, start_year, +2 more. Returns: query, metadata, warnings, observations
get_source_setupBInspect
Explain source access requirements without exposing server secrets.
Inputs: source_id (required). Returns: source, registration_url, credential_policy, server_configured, +1 more
list_sourcesBInspect
List supported and planned official data sources and their access characteristics.
Inputs: topic. Returns: total, sources, warnings
resolve_geographiesAInspect
Resolve country names or codes to ISO 3166-1 alpha-3 codes such as GHA and KEN.
Inputs: names_or_codes (required). Returns: resolved, unresolved
search_indicatorsCInspect
Rank official indicators; returns match evidence, retrieval health and source failures.
Inputs: query (required), limit, source_ids. Returns: total, results, warnings, cache_hit, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool has a distinct purpose: listing sources, retrieving setup details, finding microdata, searching indicators, FAOSTAT-specific queries, geography resolution, metadata retrieval, observation retrieval, and comparison. Descriptions clearly differentiate overlapping areas like list_sources vs find_microdata.
All tool names follow a consistent snake_case verb_noun pattern (e.g., list_sources, get_observations, compare_observations). Prefixing FAOSTAT-specific tools with 'faostat_' adds a clear namespace without breaking the pattern.
With 10 tools, the server is well-scoped for discovering, searching, and retrieving development indicator data. This count is within the ideal range and each tool earns its place by covering a distinct part of the workflow.
The surface covers the full discovery-to-retrieval pipeline: source enumeration, search, metadata, observations, and comparison. Minor gaps exist (e.g., no bulk download or time-series filtering), but these are not severe dead ends for typical use cases.
Maintenance
Related MCP Connectors
Official statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries.
Query 29,500+ World Bank development indicators for 200+ countries across 60+ years.
Access World Bank development indicators for 200+ countries.
Macroeconomic and other official data from 170+ publishers, resolved from natural language with provenance.
Related MCP Servers
- FlicenseBqualityCmaintenanceEnables AI assistants to interact with the World Bank open data API, allowing for listing and analysis of indicators across available countries.150-
- AlicenseBqualityDmaintenanceProvides access to the World Health Organization's Global Health Observatory data, enabling AI assistants to search, retrieve, and analyze comprehensive health indicators, country statistics, disease burden data, and regional health trends through WHO's OData API.1MIT

Data360 MCP Serverofficial
FlicenseNot gradedqualityBmaintenanceProvides LLM agents direct access to World Bank development indicators, enabling search, validation, and retrieval of data on topics like GDP, poverty, and gender equality.45-- AlicenseAqualityFmaintenanceEnables AI agents to discover, retrieve, compare, and analyze trusted macroeconomic statistics from central banks and international organizations, resolving concepts to official series with provenance and validation.6MIT