mcpField
H
Hiasynth Humanity — European demographics & market data

Hiasynth Humanity — European demographics & market data

Remote
hiasynth.coBusiness & Marketing0Updated 2w ago

About Hiasynth Humanity — European demographics & market data

Hiasynth Humanity is an MCP server for market and demographic analysis across Europe, for teams assessing customer segments and locations. It combines modelled household data into aggregate answers at scales down to 1 km².

Key features

  1. 01Analyze segment size and locations
  2. 02Describe area demographics and spending
  3. 03Compare and rank places
  4. 04Identify audience channels and brands
  5. 05Run structured population queries

Use cases

  1. 01Estimate a customer segment in a region
  2. 02Compare neighbourhoods for a store location
  3. 03Find media channels for a target audience

MCP support

Exposes read-only population analysis tools to MCP clients over streamable HTTP. Access uses OAuth 2.1 or an API key; responses contain aggregates rather than individual records.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.hiasynth.co
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Hiasynth Humanity

Hiasynth Humanity

Query humanity.

Find your customers, size your market and choose your next location anywhere in Europe, by asking your AI assistant in plain words. See who lives around each neighbourhood you're considering, how many people match your customer and the towns where they cluster most, and which channels reach them, from a whole country down to 1 km².

Every answer is computed from Hiasynth Humanity, a modelled population of all 522 million Europeans: each person in a household, each household in its neighbourhood, with about 700 attributes per person, from age and income to values, media habits and what the household spends. So you can combine anything, in any place.

Add to Claude Add to Cursor Install in VS Code Install in VS Code Insiders

https://mcp.hiasynth.co

Streamable HTTP · OAuth 2.1 (sign in with your Hiasynth account) or an API key · every tool read-only.

Connect

ClientHow
Claude (web, desktop, mobile)Add from Claude's connector directory. Guide
ChatGPTSettings → Apps → Create → paste the address. Guide
Claude Codeclaude mcp add --transport http hiasynth https://mcp.hiasynth.co Guide
Cursor / VS CodeThe buttons above.
Gemini CLIgemini extensions install https://github.com/hi-synth/hiasynth-mcp-server
Anything elseRemote MCP over streamable HTTP. Guide

Headless clients send an API key from hiasynth.co/app/mcp as Authorization: Bearer …:

{
  "mcpServers": {
    "hiasynth": {
      "url": "https://mcp.hiasynth.co",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Build it into your product

The same server is an API for your features and agents: size a market inside a CRM and show where to dig next, tie a marketing tool's personas to the actual population, or show the wallet size of any neighbourhood.

  • Auth: OAuth 2.1 for user-facing apps, or a server-side API key from hiasynth.co/app/mcp (Authorization: Bearer …).
  • Responses: structured JSON with the numbers already computed: counts, shares, lift against the local baseline, top places, and a confidence tier. Aggregates only, never individual records.
  • Fine control: query_population takes a structured spec (group-by, filters, count/share/avg) for pipelines that need exact shapes.
  • Any MCP client library works: the official SDKs, the Claude and OpenAI APIs' MCP connectors, LangChain, or plain JSON-RPC over HTTPS.

What analyze_market returns for renting families with above-median income in Bavaria (trimmed):

{
  "headline": "418,921 households (6.81% of Bayern). Biggest markets: München, Nürnberg.",
  "segment_size": { "count": 418921, "share_pct": 6.81, "population": 6153349 },
  "core_markets": [
    { "name": "München, Landeshauptstadt", "count": 43674, "local_share_pct": 6.51, "lift": 0.96 },
    { "name": "Würzburg", "count": 5272, "local_share_pct": 8.41, "lift": 1.23 }
  ],
  "hotspots": [
    { "name": "Sonthofen, St", "count": 1111, "local_share_pct": 10.56, "lift": 1.5 }
  ],
  "confidence_tier": "medium",
  "computed": "3 attribute filter(s) over 6,153,349 households at municipality resolution; counted, not estimated"
}

Full reference: Build with Hiasynth.

Try asking

  • How many renting families with above-median income live in Bavaria, and where do they cluster?
  • What do households in La Croix-Rousse, Lyon, spend on restaurants and cafés?
  • Who lives in Södermalm, Stockholm — and how is it different from the rest of Sweden?
  • Which media channels reach women aged 25–40 in the top income quartile in France?
  • Compare Munich, Hamburg and Vienna for affluent 30–45 year olds.
  • What does a typical household in Porto spend on eating out, and how does its carbon footprint compare?

Tools

ToolWhat it answers
analyze_marketHow many people match a segment, who they are, and where they cluster.
describe_areaWho lives in a place — demographics, values, economics, media, spending, footprint.
reach_audienceWhich channels, values and brands over-index for a segment.
compare_placesSide-by-side comparison of places for one segment.
rank_placesRank regions or towns for a segment.
sample_personaRepresentative personas (statistical composites, never a real row).
resolve_placeTurn a name, code, postcode or point into the exact area used.
query_populationStructured group-by for agent builders.
list_attributesSearch the attribute catalogue.

All tools are read-only (readOnlyHint: true), return aggregates only, and suppress any cell under the privacy floor. Special-category attributes are never broken down below region level.

Links

Docs · Pricing · Privacy · Terms · Support

This repository holds the public listing files (registry server.json, Gemini CLI extension). The server itself is operated by Hiasynth AB.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.