
UNHCR Population Data MCP Server
Provides access to UNHCR refugee statistics through a standardized interface, allowing AI agents to query data by country of origin, country of asylum, and year.
README
UNHCR Population Data MCP Server
This MCP (Model Context Protocol) server provides access to UNHCR population data through a standardized interface. It allows AI agents to query UNHCR’s Refugee Population Statistics Database by country of origin, country of asylum, and year(s).
Features
- Query total population data by country of origin, country of asylum, and year(s)
- Get refugee/asylum seekers counts for specific country of origin and asylum
- Access country profiles with both origin and asylum statistics
- View global refugee statistics by year
Installation
Prerequisites
- Python 3.8 or higher
- pip or another Python package manager
Setup
-
Clone this repository:
-
Install dependencies:
pip install -r requirements.txt
Usage
Running Locally
To run the server locally in development mode:
python app.py
This will start the MCP server in development mode, allowing you to interact with it using the MCP Inspector or other MCP clients.
Deploying to Smithery.ai
This server is configured for deployment on Smithery.ai, a platform for hosting MCP servers.
- Add your server to Smithery (or claim it if it's already listed)
- Click Deploy on the Smithery Deployments tab on your server page
API Endpoint
This server interacts with the UNHCR Population API:
https://api.unhcr.org/population/v1/population/
Query Parameters
cf_type
: Always set to "ISO"coo
: Country of origin filter (ISO 3-letter country codes, comma-separated for multiple)coa
: Country of asylum filter (ISO 3-letter country codes, comma-separated for multiple)year
: Year filter (comma-separated for multiple years)
MCP Tools
get_population_data
Get raw population data from UNHCR with optional filtering.
Parameters:
coo
(optional): Country of origin filter (ISO 3-letter code, comma-separated for multiple)coa
(optional): Country of asylum filter (ISO 3-letter code, comma-separated for multiple)year
(optional): Year filter (comma-separated for multiple years)
get_refugee_count
Get refugee count for a specific country of origin.
Parameters:
coo
: Country of origin (ISO 3-letter code)coa
(optional): Country of asylum filter (ISO 3-letter code)year
(optional): Year filter
get_asylum_count
Get asylum statistics for a specific country of asylum.
Parameters:
coa
: Country of asylum (ISO 3-letter code)year
(optional): Year filter
MCP Resources
unhcr://countries
Get a list of countries with their ISO codes.
unhcr://stats/{year}
Get global refugee statistics for a specific year.
Parameters:
year
: The year to get statistics for
unhcr://country/{country_code}
Get a profile for a specific country, showing both origin and asylum statistics.
Parameters:
country_code
: ISO 3-letter country code
License
MIT
Acknowledgments
This project uses data from the UNHCR Refugee Population Statistics Database.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.