Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Placepoint API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fplacepoint.no%2Fplacepoint" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fplacepoint.no%2Fplacepoint" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Placepoint API.
Resolve an address or a lat and lon coordinate to the property it belongs to
Pull a property's owners, tenants, registered transactions, comparable transactions, and valuation by its cadastreId
Check a property's zoning plans, building permits, encumbrances, utilization, energy certificates, and natural-hazard risks
Look up as many as 100 cadastreIds in one bulk call and receive a notFound list for the ids that do not resolve
GET STARTED
Profile a company by organisation number with its roles, shareholders, group structure, premises, employee-count history, and financial statements
Subscribe to signed CloudEvents webhooks for events such as OWNER_CHANGED or BUILDING_PERMIT_CHANGED on one property or company
Read area statistics and land allocation tenders for an areaId
Patterns agents use Placepoint API for, with concrete tasks.
★ Agent-Driven Property Due Diligence via Jentic
An AI agent preparing a property brief for a buyer, lender, or broker resolves the address to a cadastreId, then gathers the owners, registered transactions, valuation, zoning plans, building permits, and natural-hazard risks for that property. Through Jentic the agent finds each Placepoint operation by intent and calls it with the OAuth token held by your own instance, assembling one brief from register data instead of several manual lookups.
Resolve the address 'Karl Johans gate 1, Oslo' with getAddress, then fetch that property's owners, valuations, zoning-plans, and risks and summarise them in one brief
Company and Ownership Checks
Compliance and credit teams checking a Norwegian or Swedish counterparty look the company up by organisation number and read its registered roles, shareholders, group structure, and filed financial statements. The listCompanyProperties operation adds the real estate the company controls, which links company exposure to property assets in one check.
Fetch company NO 923609016 with getCompany, then list its shareholders, group-structure, and financial-statements and flag any shareholder holding more than 25 percent
Property Change Monitoring with Webhooks
Portfolio managers and lenders who need to know when something changes on a property create a subscription with a target, a list of events such as OWNER_CHANGED, TENANT_CHANGED, or TRANSACTION_REGISTERED, an HTTPS webhookUrl, and a shared secret. Placepoint delivers signed CloudEvents with a Placepoint-Signature header and retries failed deliveries with exponential backoff, so a receiver verifies the HMAC and deduplicates by event id.
Create a subscription for PROPERTY target country NO and a given cadastreId with events OWNER_CHANGED and BUILDING_PERMIT_CHANGED, a webhookUrl, and a 32-character secret, then list subscriptions to confirm it
Bulk Portfolio Enrichment
Teams holding a list of properties enrich them in batches with the createPropertyLookups operation, which accepts up to 100 cadastreIds per call and returns the resolved properties plus a notFound list. Each id is metered individually against the property:read quota, so the notFound list shows exactly which identifiers need correcting.
Send 80 cadastreIds to createPropertyLookups for country NO and report which ones came back in notFound
41 endpoints — the placepoint api serves the nordic property and company register data behind placepoint fusion through one rest interface.
METHOD
PATH
DESCRIPTION
/addresses/{country}/{address}
Resolve an address to a property
/properties/{country}/{cadastreId}
Get a property
/properties/{country}/{cadastreId}/owners
List a property's owners
/properties/{country}/{cadastreId}/valuations
Get a property's valuation
/properties/{country}/lookups
Look up properties in bulk
/companies/{country}/{id}
Get a company
/companies/{country}/{id}/shareholders
List a company's shareholders
/subscriptions
Create a change-event subscription
/addresses/{country}/{address}
Resolve an address to a property
/properties/{country}/{cadastreId}
Get a property
/properties/{country}/{cadastreId}/owners
List a property's owners
/properties/{country}/{cadastreId}/valuations
Get a property's valuation
/properties/{country}/lookups
Look up properties in bulk
/companies/{country}/{id}
Get a company
/companies/{country}/{id}/shareholders
List a company's shareholders
/subscriptions
Create a change-event subscription
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Placepoint by hand means running the OAuth client credentials exchange at /auth/token, requesting the right resource:action scopes, refreshing tokens, and verifying signed webhook deliveries. Through Jentic you install once, import Placepoint from the API Directory, store the client credentials once, and your agent calls it.
Permission scoping
Placepoint puts the country and cadastreId in the URL path (/properties/{country}/{cadastreId}/...), and the organisation number in company paths, so a rule can pin your agent to one property or one company. You choose the operations it may call, so subscription creation and deletion are not included unless you add them.
Credential isolation
Your Placepoint client credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find the owners of a property' or 'get a company's shareholders', and Jentic returns the matching Placepoint operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Placepoint API through Jentic.
What authentication does the Placepoint API use?
The Placepoint API uses OAuth 2.0 with the client credentials grant, per its OpenAPI spec: exchange your client id and secret at /auth/token for an access token. Scopes follow a resource:action pattern, such as property:read, company:read, person:read for owner and shareholder personal fields, area:read, and subscription:write. The token endpoint, the well-known discovery document, and the spec itself are open. Through Jentic the client credentials are stored encrypted on your own instance and injected at call time.
Is there a Placepoint MCP server?
You don't need an MCP server to give your agent Placepoint. Jentic connects it directly from the API Directory: import Placepoint, store your client credentials once, and your agent can look up properties and companies straight away. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.
Can I limit what my agent is allowed to do with the Placepoint API?
Yes. Write a rule that allows only the read operations under /properties/NO/{cadastreId} for a single cadastreId, so the agent can pull owners, valuations, and risks for that one property and cannot create or delete subscriptions, and every call it makes is logged.
Which countries does the Placepoint API cover?
Property and company paths take a country path parameter with an ISO 3166-1 alpha-2 code; the spec lists NO and SE. A 404 on the bulk lookup means the country's cadastre register itself is not served, while an individual id that does not resolve comes back in the notFound list.
What are the rate limits for the Placepoint API?
The OpenAPI spec meters usage per scope quota, and on the bulk lookup each requested cadastreId counts as one call against the property:read quota. The spec does not publish quota sizes; check https://docs.placepoint.no/developer/guide/ for the limits on your agreement.
How do I look up a property's owners with the Placepoint API through Jentic?
Search Jentic for an intent like 'find the owners of a property', import Placepoint, and store your client credentials once. Your agent then calls listPropertyOwners at /properties/{country}/{cadastreId}/owners, resolving an address first with getAddress if it does not have the cadastreId. To run it on your own infrastructure, install Jentic One from its GitHub repo.
How are Placepoint webhook deliveries signed?
Each delivery is a CloudEvents 1.0 envelope with a Placepoint-Signature header shaped t=timestamp,v1=signature, where the signature is a hex HMAC-SHA256 keyed on the secret you set when creating the subscription. Failed deliveries retry with exponential backoff for up to 24 hours, and delivery is at-least-once, so deduplicate by event id.
For Agents
Resolve addresses and coordinates to properties, pull a property's owners, transactions, valuation, zoning, and risks, and look up companies with their shareholders, group structure, and financial statements. Subscribe to signed webhooks when an owner, tenant, or permit changes.
Use for: I need to find the owners of a Norwegian property, Resolve this street address to a cadastre property, Get the latest valuation and comparable transactions for a property, Check whether a property has natural-hazard risks or encumbrances
Not supported: Does not handle property listings, mortgage applications, or map tile rendering. Use for Nordic property, company register, and change-event data only.
The Placepoint API serves the Nordic property and company register data behind Placepoint Fusion through one REST interface. Properties are keyed on country code and cadastreId (the Norwegian matrikkelnummer), with sub-resources for owners, tenants, transactions, valuations, zoning plans, building permits, energy certificates, natural-hazard risks, and boundaries. Companies are keyed on country code and organisation number, with roles, shareholders, group structure, financial statements, and the properties they control. Area statistics, land allocation tenders, and webhook subscriptions for change events such as OWNER_CHANGED round out the surface.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>