Placepoint MCP server

The Placepoint MCP servers make all of Placepoint, both data and functionality, available in Claude. You write what you want to know, in whichever language you use. Claude retrieves Placepoint's combined, contextualised and quality-assured data (matrikkel, Grunnboken, company and map data and more), combines it with open sources and your own datasets, and puts it all together into an answer, a table, a map, an interactive dashboard or a PDF report.

There are two servers. Placepoint MCP gives Claude the registers and the map layers. Placepoint Dataset MCP gives Claude your projects and datasets in Placepoint Fusion, so the result of an analysis can become a map layer you keep working with, and your lists can meet the registers in the same question. See Two servers, one conversation.

⚠️ The Placepoint MCP server is an experiment. We are trying it out together with leading professional communities in the industry to learn what is useful, and the outcome is open: the result may be improvements in the Placepoint product, entirely new initiatives, or both. It has not been decided whether the MCP server itself becomes a product, and if so in what form, at what price or for whom. Features, data and access may change or be removed without notice. Do not build workflows you depend on around this yet, and always verify against official sources before the results are used for decisions.

What MCP is

MCP (Model Context Protocol) is a standard way to give an AI assistant access to a selection of tools and data sources. When the Placepoint MCP server is connected in Claude, Claude can look things up in our property registers while you talk, instead of guessing from what the model remembers. You do not need to know anything about matrikkel structure, field names or APIs. You ask, Claude retrieves.

The foundation is the same as in Placepoint: around 2,300 data sources and map layers from public agencies, kommuner and commercial vendors, covering 3.5 million matrikkelenheter, 1.1 million active companies and over 30 million ownership relationships between companies, owners and property. Every single dataset, what it contains and where you find it at the source, is listed on Data and sources. The scope in numbers is on Placepoint in numbers.

Two servers, one conversation

	Placepoint MCP	Placepoint Dataset MCP
What Claude gets	The registers and the map layers: matrikkel, Grunnboken, companies, land use plans, risk, travel time	Your projects and datasets in Placepoint Fusion
Direction	Reads. Nothing you ask about changes anything in Placepoint	Reads and writes. Claude can create datasets, add rows and columns, and change the style of the map layer
Typical question	"Who owns [address], and what is registered on the property?"	"Upload our tenant list, link it to the matrikkel and show it in the map."
The result	Answer, table, map, dashboard or PDF report in Claude	A dataset in your project, visible and editable in the map
Sign-in	Your Placepoint user. You get the server URL from your contact at Placepoint	Your Placepoint user. Access follows the projects you have access to

Together they cover the workflow from question to delivery. Claude finds the properties with Placepoint MCP, and saves the result as a dataset with Placepoint Dataset MCP. The next time you open the project in Placepoint Fusion, the list is there as a map layer. The other way round, you upload your own list, a portfolio, a customer list or a tenant register, and ask about it together with the registers: which properties on the list have a new owner or a new mortgage since last time?

From days to minutes

Much of the most important analysis work around property is still manual: find the right register, extract the data, quality-assure it and put everything together into something the board, the credit committee or the client can read. It takes days or weeks, often requires an external consultancy, or never gets done because it is too extensive to be prioritised.

With the Placepoint MCP server, Claude does the same work in minutes, and delivers the result as a report, an interactive dashboard or a presentation. Examples of work that today ties up skilled people for days:

• Property companies and managers: portfolio and board reports across SPV structures, tenant overview per building with how long each tenant has been registered, ESG status for the whole portfolio.
• Law firms: due diligence with a review of encumbrances (mortgages, easements, rights of way and subdivision bans) for many properties at once, and mapping of ownership chains from the ultimate owner down to each individual company.
• Brokers and advisers: material for sales prospectuses and valuations, buyer assessment of a counterparty, location analyses for chains and businesses.
• Banking and insurance: climate risk and nature risk per property or portfolio (flooding, landslides, quick clay, surface water), and credit assessments with traffic lights per risk theme.

And you do not need to look up one property at a time. Ask about a whole street, a block or a district, and Claude does the job for all the properties in the area at once. The prompt "Check the whole of John Colletts allé, where can new buildings go, make a report" produced a 15-page report that went through all 72 land properties in the street, with a map and an assessment per address. Along the way, Claude read the plan documents themselves, and found four addresses in the middle of the street that are not covered by the building ban that stops all the neighbours. That exception is not in any map database. It is in the decision on the extended building ban, because the requirements are in the planning provisions, not in the colours on the plan map. Going through 72 properties and their plan documents by hand is days of work; here it took minutes.

The foundation is the data Placepoint has already collected, quality-assured and put in context: see Data and sources. Claude retrieves from the same foundation, so you do not have to search each individual source and stitch it together yourself.

What you can do with Placepoint's MCP server

The examples below are finished reports and analyses that colleagues and pilot users have already made with the Placepoint MCP server. Replace the placeholders in square brackets with a real address, a matrikkel number or an organisation number:

• Look up [address] or [matrikkel number] and gather facts about the site, buildings, units, owners and tenants in one place, the way the property panel and the tab for units and tenants do it in Placepoint Fusion.
• Search and filter properties on criteria across the whole of Norway, for example year built, building type, area or tenants, and export the result.
• Retrieve the full land register extract for [matrikkel number] and summarise encumbrances: mortgages, easements, rights of way and subdivision bans.
• Mass-scan land registers and encumbrances for a whole area at once, for example all matrikkel numbers within [area].
• Map the companies behind [matrikkel number]: ownership structure from the ultimate owner down to the subsidiaries, roles, shareholders and annual accounts, as in the company panel.
• Make a due diligence report for [matrikkel number] with a legal, technical and financial review.
• Make a credit and risk report for [matrikkel number].
• Make a climate risk and nature risk report for [matrikkel number] for use in a credit assessment, with traffic lights (red, amber, green) per theme such as flooding, landslides, quick clay, surface water, cultural heritage and threatened species.
• Make a climate risk and sustainability analysis for a head office at [address], with tenants, certification and travel time.
• Check risk and the framework around [matrikkel number]: flooding, landslides, quick clay, zoning and municipality plans, nature types and protected areas, shown on a map with the risk map layers.
• Find out which land use plans apply to [matrikkel number], including municipality plan proposals, and get the plan map shown together with the property boundaries, in line with the zoning map layers.
• Retrieve the plan documents for a plan, for example provisions and the plan description, and have them read and summarised, not just listed.
• Search for land use plans in an area or by plan name, and see plan maps and plan proposals together with what has been adopted, including detailed zoning plans and area zoning plans.
• Retrieve historical aerial photos around [matrikkel number] and compare the area year by year.
• Calculate travel time and reach by car, public transport, bicycle or on foot, and find properties within a given travel time.
• Do a location analysis: the best place for a new shop in [area], or suitable sites for data centres in Norway.
• Make an investment and development analysis for [matrikkel number]: demolish or extend, yield, plot ratio, development potential and possible land use.
• Make a buyer assessment of [org. no.] that wants to take over [matrikkel number].
• Retrieve the whole property portfolio of [company], including properties owned indirectly through subsidiaries and SPV chains.
• Make a portfolio or board report for [org. no.], of the same type as the reports in Placepoint Fusion.

With Placepoint Dataset MCP in addition:

• Save a search result as a dataset in your project, for example all logistics properties over 10,000 m² in [kommune] with owner and year built, and get it as a map layer in Placepoint Fusion.
• Upload an Excel file and have the rows linked to the matrikkel on address or matrikkel number, the way dataset upload does it in the platform. If you have the geometry in GeoJSON or WKT, you put it in a column in the spreadsheet.
• Add kommune, grunnkrets (basic statistical unit) or postcode as columns in a dataset, and sum or count rows per area.
• Ask about your own rows together with the registers: which properties in [dataset] have changed owner, got a new mortgage or lie in a flood zone?
• Calculate travel time from each point in a dataset, or find the shortest route that visits all of them.
• Tidy up a dataset: change values, add columns, hide columns and set colours and symbols on the map layer.

Examples from the trial

Pilot users have, among other things, made a 25-page sustainability report for a well-known head office in Oslo, due diligence and climate risk reports, mass scanning of land registers for whole complexes, and a lead list with 1,517 properties for a roofing contractor. All the examples, with a complete report example to download, are on MCP examples.

How reports are delivered

Reports are delivered as HTML by default, because that is fastest and lets you read the result straight away. Ask for PDF when you need a document to send on, and choose between one long page or real paginated pages. PDF takes longer to make, and Claude tells you about the time needed before it starts.

When a plan is discussed in a report or analysis, Claude reads the provisions and the plan description first, instead of building the text on the plan name alone. Property lookups also suggest plan status and a hazard sweep (landslides, flooding, quick clay and similar) as the next step, so zoning and risk are not skipped. The reports resemble the ones you make in Analyze and reports.

Which data is available

Claude retrieves from the same sources that underpin Placepoint:

• The matrikkel: properties, buildings, units, area and year built for the whole of Norway, as in the property panel and the building panel.
• Grunnboken: title history and registered encumbrances, with a full land register extract on request.
• Company data: roles, ownership, the shareholder register and annual accounts from Brønnøysundregistrene (BRREG) and related sources, corresponding to the company panel.
• Transactions: registered changes of ownership and sales, including company sales.
• Map layers: around 2,300 sub map layers spread across around 170 map services from, among others, Norges vassdrags- og energidirektorat (NVE), Norges geologiske undersøkelse (NGU), Miljødirektoratet, DIBK, Geodata AS and Placepoint. Covers, among other things, flooding, landslides, quick clay, zoning and municipality plans, nature types and protected areas, energy labelling, demographics, public transport coverage and emergency services.
• Land use plans: five datasets covering adopted zoning plans, plan proposals under consideration, municipality plan, municipality plan proposals and notices of plan initiation, including Oslo. With plan maps and plan documents (provisions, plan description and more) as PDF, which Claude reads where they exist. Lookups per property use the property's actual boundaries, not just a point, so the hits are more accurate. If plan data is missing for a property, Claude says so instead of describing the property as unzoned. The same plans are in the zoning map layers.
• Travel time and traffic: routes, isochrones and travel time matrices with up to 100 × 100 points, the same foundation as Travel distance in Analyze.
• Aerial photos: historical and current images from Norge i bilder.

In total, Claude retrieves from over 130 datasets supplied by around 25 organisations. Most are open, public sources, among others Kartverket, Brønnøysundregistrene, NVE, NGU, Miljødirektoratet, DIBK, Artsdatabanken, Statistisk sentralbyrå (SSB) and Statens vegvesen. In addition there are commercial vendors and services, among others Geodata, Microsoft Azure Maps (background maps and places) and TravelTime (travel time).

You find an overview on Data and sources, and who supplies what on Vendors.

Can be combined with other systems

The Placepoint MCP server is not meant to replace the specialist systems you already use, but to work alongside them. The property data Claude retrieves can be combined with information from other solutions, for example systems for physical property management (leases, areas, operation and maintenance), ERP and finance systems, and specialist systems for management, operation and maintenance of public building stock. Then you can use Placepoint for matrikkel, Grunnboken, company and risk data, and your own systems for what they do best, in the same analysis or report.

In Claude Desktop, in Cowork and in Claude Code, you connect to other MCP servers alongside Placepoint's yourself. The agent panel in Placepoint Fusion will get connections to external systems that the administrator at the customer sets up; which systems are relevant is described on Agent in Placepoint Fusion.

Agent panel in Placepoint Fusion

The MCP server is also available as a pilot inside Placepoint Fusion, in a separate agent panel. There you ask the same questions directly in the platform, without Claude Desktop, Cowork or Claude Code. The Agent uses both MCP servers, controls normal Fusion functionality such as the map and panels, and searches the user documentation when you wonder how something is done. The panel is being trialled with selected users. Three of the example prompts at the bottom of the page apply only in Claude Desktop: historical aerial photos, density maps and export to a spreadsheet. The panel makes neither images nor files, so there you get the answer as text and map links.

Personal data is not available

The Placepoint MCP server does not give out information about private individuals. When Claude retrieves a land register extract, personal names and national identity numbers are removed automatically before the data reaches the model, and private individuals are shown as Private person. So you cannot use the MCP to find out who owns a home, or to look up individuals. Companies, roles and ownership structure are open data and are included.

This applies regardless of the access level your account has elsewhere in Placepoint. The extended access to personal data that some professional users can get in the platform itself (documented "legitimate interest") does not apply to the MCP.

Placepoint Dataset MCP works with your own datasets, and sees only the projects your Placepoint user has access to. The content of the files you upload is your responsibility in the same way as when you upload them in the platform.

Short example prompts

Feel free to start with "Use Placepoint MCP" and ask the question in whichever language you use:

• "Retrieve the land register extract for [matrikkel number] and summarise which encumbrances are on the property."
• "Check whether the property [matrikkel number] lies in a flood or landslide-prone area, and show it on a map."
• "Which zoning plans and municipality plans apply to the property [matrikkel number]?"
• "Check the whole of [street]: where can new buildings go? Make a report."
• "Which sites in [street] are large enough to be subdivided?"
• "Has plan work been announced near [address]?"
• "Which addresses in [street] are not worth looking at?"
• "Retrieve the provisions and the plan description for the plan that applies to [matrikkel number], and summarise what is permitted in terms of plot ratio, heights and purpose."
• "Show all historical aerial photos around the property [matrikkel number], laid out neatly with metadata."
• "Find the best places to set up a new shop near [place]."
• "Make a risk report for [address]."
• "Make a risk assessment of org. no. [org. no.] as buyer of the property [matrikkel number]."
• "Make a portfolio report for org. no. [org. no.]."
• "Make a full portfolio overview for org. no. [org. no.]: all properties with geography and a map of the main cluster, ownership structure from the ultimate owner down to the SPVs with flags for deleted companies and companies with negative equity, all tenants per building with how long each tenant has been registered, and an ESG profile per building."
• "Find the 10 best premises for a distribution centre for a company that has to make deliveries physically in [area], ranked by driving time."
• "For [address]: make a 3D drawing where the existing building is removed and a new Rema 1000 building is drawn in."
• "Make a portfolio report about all the properties [company] (org. no. [org. no.]) owns in [place/area]."
• "How many active properties are there in [kommune]?"
• "Which kommuner have the most sections?"
• "Which properties does Equinor rent in [kommune]?"
• "Show detached house density in [kommune] as a map."
• "Export all properties with tenants in [kommune] to a spreadsheet."

With Placepoint Dataset MCP:

• "Make a dataset in the project [project] with all commercial properties over 5,000 m² in [kommune], with owner and year built."
• "Upload our tenant list, link the rows to the matrikkel on address and show which ones did not get a match."
• "Add kommune and grunnkrets to each row in [dataset], and count rows per kommune."
• "Which properties in [dataset] have got a new title holder or a new mortgage in the past year?"
• "Find the shortest route that visits all the points in [dataset] by car from [address]."
• "Set the colour on [dataset] by year built, and hide the columns we do not use."

How to get started

We are inviting a selection of leading property companies, law firms, brokerages, banks and insurance companies to experiment and learn together with us. We work out what is most valuable together, and what you teach us shapes both the Placepoint product and whatever the MCP server may become.

If you want to take part, get in touch via placepoint.no/selskap/kontakt.

How to install

Both servers are added as "Custom MCP", and they work everywhere Claude accepts custom MCP servers: in Claude Desktop, in Claude on the web, in Cowork and in Claude Code. The same URL and the same sign-in wherever you connect.

In Claude Desktop, in Claude on the web and in Cowork, the procedure is described in Get started with custom connectors using remote MCP. It is the same for both servers: add the URL you get from your contact at Placepoint, click Connect and sign in with your Placepoint user. You sign in once per server, with the same user you use in Placepoint Fusion.

In Claude Code you add the server from the terminal and sign in with /mcp:

claude mcp add --transport http placepoint <URL-en fra Placepoint>

• Placepoint MCP: the registers and the map layers. Access follows your user, not the URL.
• Placepoint Dataset MCP: your projects and datasets. Claude sees the same projects and datasets that you see in Placepoint Fusion.

If new tools are missing from the list, go to Settings, Customize, Connectors, select Placepoint, click the three dots and select Refresh tools list. Take questions, missing access and feedback up with your contact at Placepoint.

Updates

New tools do not appear until the connector has been updated. If they are missing in Claude, go to Settings, Customize, Connectors, select Placepoint, click the three dots and select Refresh tools list.

03/09/2026:

• Sign-in with your Placepoint user on both servers. You click Connect in Claude and sign in the way you do in Placepoint Fusion. Access follows the user instead of the URL.

02/09/2026:

• Placepoint Dataset MCP: a separate server for your projects and datasets in Placepoint Fusion. Claude can create datasets from a search result, upload and matrikkel-link files, add kommune and grunnkrets as columns, sum per area, calculate travel time and optimise routes, and set the style on the map layer. You sign in with your Placepoint user, and access follows your projects.

19/08/2026:

• Land use and zoning plans now cover five datasets: adopted zoning plans, plan proposals under consideration, municipality plan, municipality plan proposals and notices of plan initiation. Oslo is included. The MCP finds the plan documents themselves, so Claude can read the provisions where they exist, and it is in the provisions that the requirements actually are, not in the colours on the plan map.
• Pilot of the MCP server inside Placepoint Fusion, in a separate agent panel: the same tools and data sources, normal Fusion functionality and search in the user documentation.

11/08/2026:

• New land use plan suite: search land use plans, retrieve plan details with the plan map, see which plans apply to a property, and retrieve plan documents (provisions, plan description and more) as PDF. Corresponds to the zoning map layers in Placepoint Fusion.
• The plan check per property only needs the matrikkel number. The property's actual boundaries are retrieved automatically and used in the lookup, which gives more accurate hits than before. Municipality plan proposals are included as a separate category.
• Plan documents are read, not just listed. If a plan is to be discussed in a report or analysis, Claude checks that provisions and the plan description have actually been read first. If plan data is missing for a property, this is stated explicitly in the delivery instead of the property appearing to be unzoned.
• Property lookups suggest plan status and a hazard sweep (landslides, flooding, quick clay and similar) as the next step, so zoning and risk are not skipped.
• Reports are delivered as HTML by default, which is considerably faster. PDF is made on request, with a choice between one long page or real paginated pages, and a note about the time needed before the heavier variant is run.
• The map tools give better error messages: unknown map layers give a message with valid alternatives, large geometries are simplified in a controlled way with a clear note, and geometries can be reused between tools without being pasted in again.
• The usage guide and the tool descriptions have been expanded, so that Claude picks the right tool for plan and zoning questions.

Reservations

• The experiment is under active development. Some tools and map layers are not fully tested and may fail.
• Both servers require sign-in with your Placepoint user. Access follows the user, so it cannot be lent out by sharing a URL.
• Claude can be wrong. The results are a starting point, not a final answer, and must be verified against official sources before they are used for decisions.
• Access, features and data may change along the way, and the whole experiment may be discontinued.