Cross-reference demographics, death rates, and well-being. 
Claude 
ChatGPT 
Cursor 
Gemini 
Windsurf 
VS Code 
JetBrains 
Vercel
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
The UK ONS Population MCP Server connects five official datasets from the Office for National Statistics. You get weekly death registrations by age and region, local well-being estimates (satisfaction, happiness), suicide data by area, macro population forecasts through 2043, and national trend data.
Use it to cross-reference mortality rates with subjective health indicators.
What your AI can do
Get weekly deaths
Pulls weekly death records for England and Wales, allowing filtering by age group, sex, or region.
Get wellbeing
Fetches national estimates of personal well-being (life satisfaction, happiness, anxiety) for the UK.
Get wellbeing local
Provides specific well-being metrics—like life satisfaction and anxiety—by individual local authority areas across the UK.
Get well-being estimates—like life satisfaction or happiness—for specific local authorities across the UK.
Retrieve weekly death statistics, allowing you to slice data by age group, sex, and specific regions in England and Wales.
Generate population forecasts for older demographics and analyze sex ratios across local authorities up to the year 2043.
Cross-reference objective data (like weekly deaths) with subjective indicators (like well-being scores) in a single analysis.
Obtain suicide registration counts specific to individual local authorities, helping flag areas needing immediate attention.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 Compatible Gemini Waiting for input…
UK ONS Population: 5 Tools for Health & Demographics
Use these five tools to retrieve specific datasets on UK demographics, mortality rates, and personal well-being estimates.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using UK ONS Population — Deaths, Well-being & Demographics on VinkiusGet Weekly Deaths
Pulls weekly death records for England and Wales, allowing filtering by age group, sex, or region.
Get Wellbeing
Fetches national estimates of personal well-being (life satisfaction, happiness...
Get Wellbeing Local
Provides specific well-being metrics—like life satisfaction and anxiety—by...
Get Suicides
Gets suicide registration counts broken down by local authority in England and Wales.
Get Population Projections
Retrieves UK population size estimates for older people and sex ratios across local...
Connect to your AI in seconds. Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The ONS Population integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with UK ONS Population — Deaths, Well-being & Demographics, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by UK ONS. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 5 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The biggest headache right now is stitching together disparate datasets.
Today, analyzing public health means jumping between five different government portals. You pull the macro demographic data from one source, run mortality stats from a second, and then find sentiment scores on a third. Each step requires manual downloading, cleaning, and cross-referencing in Excel—it’s slow, error-prone, and you lose context every time.
With this MCP Server, your agent handles the entire pipeline. You ask one question: 'How does population aging affect local anxiety?' The server calls `get_population_projections`, runs it against `get_wellbeing_local` for all regions, and gives you a direct comparison. It turns a week of data wrangling into one conversation.
The get_suicides tool: Pinpointing local health crises.
Manually compiling suicide rates involves searching by region, then downloading the sheet, and finally aggregating those numbers to compare them against other metrics. This process is tedious and often leaves you with data that isn't perfectly aligned geographically.
Now, your agent calls `get_suicides` directly. You specify 'local authority X,' and it gives you clean, actionable figures immediately. It removes the entire manual aggregation step and puts the focus back on what the number means.
What your AI can actually do with this
You're looking at five massive datasets from the Office for National Statistics that connect demographics, mortality rates, and how people actually feel in England and Wales. This isn't just raw data; it’s a platform for cross-referencing objective health metrics with subjective well-being indicators across local areas.
When you need to track regional mortality trends, you use get_weekly_deaths. It pulls weekly death records for both England and Wales, letting you filter the numbers by age group, specific sex, or geographic region. You don't just get a total count; you can isolate exactly who’s passing and where they're coming from.
If pinpointing localized health crises is your goal, get_suicides gives you suicide registration counts broken down specifically by local authority in England and Wales. This lets you immediately flag areas that need urgent attention because the data isn't national—it’s hyper-local.
To understand population shifts over time, run get_population_projections. It retrieves UK population size estimates for older people and sex ratios across every local authority all the way up to 2043. This lets you model growth patterns and demographic imbalances years in advance.
For well-being metrics, you've got two angles. First, get_wellbeing fetches national estimates of personal life satisfaction, happiness, and anxiety for the entire UK population. That gives you a top-level view of general sentiment. Second, if you need to analyze localized well-being, use get_wellbeing_local. This provides specific metrics—like life satisfaction or anxiety scores—broken down by individual local authority areas across the UK.
What this really lets you do is correlate risk factors. You can take objective numbers from get_weekly_deaths and cross-reference them directly with subjective data points pulled from get_wellbeing_local. For example, you might check if a spike in anxiety scores in one local area correlates with an uptick in weekly deaths or suicide registrations that week.
You can analyze localized well-being by pulling happiness or life satisfaction estimates for specific authorities. You're not limited to national averages; the data structure lets you drill down into single postal areas and see how their unique socio-economic factors affect reported mental health metrics like anxiety levels.
Model population growth when you combine get_population_projections with other datasets. You can project future demographic pressure—like an aging population or a specific sex ratio skew—and then overlay current well-being scores to estimate what kind of resource strain that shift might cause. You're building a narrative: the hard data meets the human experience.
It’s about connecting these disparate streams: mortality, life satisfaction, projected demographic changes, and suicide counts. You use get_weekly_deaths for regional trends, you check get_suicides for acute localized risk, and you pair both with the national or local sentiment data from the two wellbeing tools to build a comprehensive picture of community health across England and Wales.
019d75e6-bf5b-716f-91d3-ac185ae44fdb 
Here's how it actually works
The bottom line is, it connects five separate ONS data sources so your AI client can run complex public health models without leaving the conversation window.
Start by defining the scope. Tell your agent which time period and geographic area you need data for (e.g., 'London' in 2023').
The server runs multiple tools—for example, calling get_weekly_deaths for mortality and get_wellbeing_local for sentiment—to pull disparate datasets.
Your agent synthesizes the output by comparing the metrics. It shows you how a dip in life satisfaction correlates with changes in local death rates or population projections.
Who is this actually for?
Public policy analysts and urban planners who need to prove a link between demographic shifts and public sentiment. This is for people tired of running five different queries in three separate government dashboards just to get a full picture.
Determining if projected population decline or local well-being drops require immediate policy intervention, using get_population_projections and get_wellbeing_local.
Building models that correlate specific mortality events (get_weekly_deaths) or suicide spikes (get_suicides) with local economic data or sentiment metrics.
Assessing the long-term viability of a region by comparing current demographic health to historical well-being scores and future population forecasts.
What Changes When You Connect
See how projected population changes affect specific regions. Use get_population_projections to forecast future numbers, then cross-check those areas with current sentiment using get_wellbeing_local. This connects the macro view to local reality.
Track acute health crises instantly. Run get_suicides alongside get_weekly_deaths to see if localized spikes in mortality correlate across different types of deaths, helping pinpoint risk factors.
Model long-term social strain. Instead of just tracking current numbers, use the combination of get_population_projections and well-being data to project when a region might become stressed due to an aging population.
Avoid siloed reporting. You don't have to open five different dashboards. Your agent calls get_wellbeing, then uses get_weekly_deaths, and compares the results side-by-side, giving you one cohesive narrative.
Get granular detail on sentiment. While get_wellbeing gives national averages, using get_wellbeing_local lets you drill down to a single council area's happiness score, making reports much sharper.
See it in action
Assessing the Impact of Aging on Mental Health
A planner needs to know if an aging population (using get_population_projections) is putting stress on local mental health. They run this data against both national well-being scores (get_wellbeing) and localized suicide rates (get_suicides). The agent reports a clear risk increase in areas with the highest projected older populations.
Investigating Post-Pandemic Community Health
A public health researcher wants to know if community death spikes are related to general discontent. They pull get_weekly_deaths for a specific time window and overlay it with the most recent local satisfaction scores from get_wellbeing_local. This identifies regional hotspots that require immediate resource allocation.
Drafting Long-Term Infrastructure Bills
A government consultant needs to justify spending on care facilities. They use population forecasts (get_population_projections) to show the predicted increase in older people, then back it up with a trend line from get_wellbeing showing decreased life satisfaction, building a compelling case for action.
Comparing Localized Health Outcomes
A journalist wants to compare two rival local authorities. They run the same metrics on both: get_suicides, get_wellbeing_local (happiness), and population data for both areas, generating a single comparative report that highlights key disparities.
The honest tradeoffs
Treating data points as independent facts
Running get_weekly_deaths in isolation and reporting 'Deaths are up 5%.' This gives a number but no context or reason for the change.
Don't stop at a single metric. Always cross-reference: If deaths spike, check if local well-being scores (get_wellbeing_local) also dropped in that region. This provides why the number changed.
Confusing correlation with causation
Seeing high anxiety and low birth rates, and assuming one caused the other without further data.
Always include population projections (get_population_projections) to check if a demographic shift (like an aging sex ratio) is the underlying cause of both trends. Data shows correlation, but you need context.
Using only national averages
Reporting that overall life satisfaction dropped, and assuming this applies equally to every local area.
Don't settle for the macro view. Use get_wellbeing_local or get_suicides to break down trends by specific regions or local authorities. The difference between London and Cornwall is massive.
When It Fits, When It Doesn't
Use this server if your primary goal is building a layered, multi-variable narrative about public health—specifically, showing how macro demographic forces (like aging populations from get_population_projections) influence micro human distress (captured by get_wellbeing_local or get_suicides). You need to prove why a trend exists.
Don't use it if you only need to track one metric over time, like simply charting death counts. For that, a dedicated time-series database is faster and simpler.
If your job is simple data retrieval (e.g., 'What was the average happiness score in 2015?'), stick to calling just get_wellbeing. But if you're trying to write a policy brief—that requires weaving together mortality, sentiment, and future population trends—this server is essential.
Questions you might have
How often is death data updated? +
Weekly. The ONS publishes provisional death registrations every Tuesday for the previous week, with a 11-day reporting lag.
Does it track personal well-being metrics? +
Yes, the ONS measures personal well-being across four indicators (O4): life satisfaction, feeling that the things done in life are worthwhile, happiness, and anxiety.
Are population figures based on the Census? +
The datasets include both decennial census data and mid-year population estimates, which are updated annually to account for births, deaths, and migration.
When I use `get_wellbeing_local`, does the dataset cover all UK local authorities? +
No, it covers specific local authority regions designated by ONS. The data structure requires you to pass a valid administrative code for the region; failing to provide this will result in an invalid input error.
What is the maximum forecast year I can use when calling `get_population_projections`? +
The projections extend up to 2043. You must specify a target date within this range, and the tool calculates ratios based on the most recent demographic model available from ONS.
If I use `get_weekly_deaths` for a specific region that isn't included in the dataset, how does it handle the request? +
The system returns an explicit 'No data available for this area' message rather than throwing a generic error. You'll need to check the supported regional codes listed in the ONS documentation.
How do I correctly interpret the scores from `get_wellbeing`? +
Most scores use 10 as the maximum, where higher is better. However, remember that for anxiety, the scoring is inverted: a lower number indicates better reported well-being.
What geographic scope must I provide when calling `get_suicides`? +
The dataset strictly covers suicide registrations in England and Wales. You cannot use this tool to pull data for Scotland or Northern Ireland; you'll need a different source for those regions.
We've already built the connector for ONS Population. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 5 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.