Kyiv -2.1%$/m² 1,480Lviv 3.0%$/m² 1,210Warsaw -1.4%$/m² 2,950Berlin 1.1%$/m² 5,100Prague -0.6%$/m² 4,300Lisbon 5.9%$/m² 4,050Odesa -3.8%$/m² 920Madrid 2.4%$/m² 3,600
InvestViewsAI Connect

Ask property data anything — inside Claude, Cursor, or any agent you already use.

Real asking prices for European property, in the AI tools you already use — every answer carries the place it covers and the period it was measured over.

  • Asking prices from listings
  • Europe, the Middle East and beyond
  • H3 cells, resolution 4–8
  • Finding places is free
  • Every figure cites its period
API tokens →Full API docs ↗

Setup

Connect your agent in minutes

There is no server to run and nothing to host. The CLI is an ordinary shell command, and the skill is a Markdown file — any agent that can run commands can use it.

  1. Get PRO and create a token

    Tokens live in your account, under API access. A new token is shown once — copy it then. It is read-only unless you ask for read/write.

  2. Install the CLI

    Homebrew on macOS. On Linux, grab the tarball from the releases page and put investviews on your PATH.

    brew install Investviews/tap/investviews

  3. Store your token

    Saved to ~/.config/investviews/config.toml, readable only by you.

    investviews auth login --token iv_live_xxxxxxxx

  4. Add the plugin

    Run both lines inside Claude Code. The first adds our marketplace, the second installs the skill.

    /plugin marketplace add Investviews/investviews-cli
/plugin install investviews@investviews-cli

  5. Ask a question in plain words

    No endpoint names, no geo ids. The skill teaches the workflow: find the place for free, check data exists, then spend one call.

    > What do flats cost in Russafa, Valencia right now?

Primary use cases

What people actually ask it

Three shapes of question, all over the same connection. Your agent resolves the place for free, then spends one metered call on the figures.

Market check

What a neighbourhood is asking in the newest complete period — price per m², by property type, down to an H3 cell.

Example promptWhat do flats cost in Russafa, Valencia right now?

Trend research

How asking prices moved over past periods, so a claim about a market has a series behind it.

Example promptHow have asking prices in Montenegro changed over the last year?

Compare places

One question across several markets, each answered from the same period so the comparison holds.

Example promptCompare price per m² in Valencia, Alicante and Málaga for the latest period.
Or browse the full API referenceEvery endpoint your agent can call, with the OpenAPI contract behind it.

Prompts to try

Paste one of these once you are connected

  • What do flats cost in Russafa, Valencia right now?
  • How have property prices in Montenegro changed over the last year?
  • Which countries do you have data for?
  • Is Alicante asking more per m² than Valencia this period?
  • Break down asking prices in Barcelona by district, coarsest cells first.
  • How fresh is your data for Lisbon, and what period does it cover?

How it is counted

Finding places is free. Only answers cost.

An agent that cannot tell a free call from a metered one either stops to ask permission it does not need, or burns quota it did not have to. Ours knows the difference, and says so on every command.

Free

Discovery

  • geo browseWalk the geography from the countries down.
  • geo searchResolve a name to a place, with its parents so two “Centro”s do not get confused.
  • coverageAsk whether a place has figures at all, and how fresh they are.
Metered

Answers

  • stats currentThe figures for the newest complete period.
  • stats historyThe same figures across past periods.
  • X-Quota headersEvery response says what is left, so an agent can pace itself.

What this data is, and is not

  • Asking prices, not sold prices. The figures come from what sellers list, not from registered transactions. That is a different number, and often a higher one.
  • Newest complete period, not today. A period closes before it is published, so the latest figure can be several weeks behind. The period is on every answer.
  • Cells, not addresses. Figures describe an H3 cell between resolution 4 and 8. A request for a finer cell is refused, never quietly answered with a coarser one.

Documentation

Everything the API can do

Written for people and for agents — every guide has a .md twin, and the whole site is available as one file.

QuickstartGet a token, resolve a place, read your first figure.AuthenticationBearer tokens, read-only vs read/write, and the 401 / 402 / 403 split.QuotaEndpoint groups, the X-Quota headers, why discovery is uncounted.DataPeriods, windows, outlier trimming, estimated cells, coverage.GeographyH3 resolutions, browsing the tree, turning a place into figures.ErrorsError shape, code meanings, retry rules and rate limits.
llms-full.txtEvery guide in one file. Paste it into any agent that takes context.