Do I need an API key for Amsterdam open data?

No, this MCP allows you to explore and query the DSO platform without an API key.

How many datasets can I access?

You can access all 122+ datasets published on the Amsterdam DSO Dataplatform.

Can I filter the data I retrieve?

Yes, the browse_dataset capability supports filters, sorting, pagination, and field projection.

Which AI clients can use this MCP?

You can use this with any MCP-compatible client like Claude, Cursor, Windsurf, or VS Code.

How does the agent know which API endpoints to use?

The agent uses the get_dataset_info capability to read the OpenAPI specification for any given dataset.

Do I need an API key?

No. The DSO dataset index, the per-dataset OpenAPI specs and the generic table access are public (OPENBAAR). Some individual datasets are marked as requiring a key in their index entry. the dataset info response shows the authentication requirement, so check it before assuming access.

How do I find the right resource names?

Call get_dataset_info for the dataset: it fetches the live OpenAPI spec and lists the exposed resources and their operations. Use the resource name (usually the Dutch word) with browse_dataset. e.g. 'stamgegevens' for bomen, 'nummeraanduidingen' for bag.

What does browse_dataset return?

A page of the dataset's rows: the items array, current page number and page size, plus a next-link (next) when more pages exist. Filters are passed as comma-separated field=value pairs and only applied when the dataset actually supports that filter field.

What is the difference between the catalog and the datasets?

The dataset index (list_datasets) covers the machine-readable REST APIs. The data catalog (list_data_products / list_data_teams) covers the city's curated catalogue of data products and the 26 data teams that produce and own them. useful for mapping a question to the right dataset or owner.

Download PDF Markdown Version

Connect Amsterdam Open Data Explorer to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your agent direct access to Amsterdam's live data platform.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

How Vinkius works: one connection, every tool, in any AI

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Complete set · 5 capabilities

The complete City of Amsterdam capability set.

These are the exact actions your AI can choose when you ask it to work with City of Amsterdam.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 5 available through City of Amsterdam.

01
List datasets
This capability finds all open datasets published by Amsterdam. You can filter the results using specific keywords or tags.
02
Get dataset info
This capability retrieves metadata and OpenAPI specifications for a single dataset. It shows you exactly which resources and operations are available.
03
List data products
This capability accesses the city's catalog of official data products. You can use keywords or pagination to find what you need.

Capability set02 / 02

04-05

2 capabilities in this set.

Part of 5 available through City of Amsterdam.

04
Browse dataset
This capability fetches actual data from any dataset resource. You can apply filters, sort results, or use pagination and field projection.
05
List data teams
This capability identifies the specific city data teams that own the various data products.

One connector, every AI

City of Amsterdam works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put City of Amsterdam to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

918ms average. Fast in production.

City of Amsterdam is checked daily against the live service.

Daily averagePeak 998ms

Sep 25Today

Fastest day: 893ms
Slowest day: 998ms
14-day trend: Improving-11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 5 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of City of Amsterdam, so you can see the experience inside your AI.

It does not authenticate your account with City of Amsterdam. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

City of Amsterdam Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_tvhA0dZJdMRAGLcaxPco8m1ZxmqgLLr4VFPfp8MM/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — City of Amsterdam capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "amsterdam-open-data-explorer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_tvhA0dZJdMRAGLcaxPco8m1ZxmqgLLr4VFPfp8MM/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? How to give Claude access to City of Amsterdam

See all the AI clients this connector works with ↑

Who it's for

Built for the work City of Amsterdam owners hand off.

This MCP is built for anyone building agents that need to interact with municipal data without manual searching.

01
Data Scientists
They hand off the task of finding and filtering specific municipal datasets to their agent.
02
Software Developers
They use the agent to prototype applications against live city data.
03
Urban Researchers
They use the agent to query specific city metrics and data products.

FAQ

Questions City of Amsterdam owners ask.

01
Do I need an API key for Amsterdam open data?
No, this MCP allows you to explore and query the DSO platform without an API key.
02
How many datasets can I access?
You can access all 122+ datasets published on the Amsterdam DSO Dataplatform.
03
Can I filter the data I retrieve?
Yes, the browse_dataset capability supports filters, sorting, pagination, and field projection.
04
Which AI clients can use this MCP?
You can use this with any MCP-compatible client like Claude, Cursor, Windsurf, or VS Code.
05
How does the agent know which API endpoints to use?
The agent uses the get_dataset_info capability to read the OpenAPI specification for any given dataset.
06
Do I need an API key?
No. The DSO dataset index, the per-dataset OpenAPI specs and the generic table access are public (OPENBAAR). Some individual datasets are marked as requiring a key in their index entry. the dataset info response shows the authentication requirement, so check it before assuming access.
07
How do I find the right resource names?
Call get_dataset_info for the dataset: it fetches the live OpenAPI spec and lists the exposed resources and their operations. Use the resource name (usually the Dutch word) with browse_dataset. e.g. 'stamgegevens' for bomen, 'nummeraanduidingen' for bag.
08
What does browse_dataset return?
A page of the dataset's rows: the items array, current page number and page size, plus a next-link (next) when more pages exist. Filters are passed as comma-separated field=value pairs and only applied when the dataset actually supports that filter field.
09
What is the difference between the catalog and the datasets?
The dataset index (list_datasets) covers the machine-readable REST APIs. The data catalog (list_data_products / list_data_teams) covers the city's curated catalogue of data products and the 26 data teams that produce and own them. useful for mapping a question to the right dataset or owner.

Explore

More in Data Analytics

Connect City of Amsterdam to Claude, Cursor, ChatGPT & more

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

List datasets

Get dataset info

List data products

Browse dataset

List data teams

Building your own app? The connector is yours to use.

City of Amsterdam Connector

Claude Desktop

Data Scientists

Software Developers

Urban Researchers

Do I need an API key for Amsterdam open data?

How many datasets can I access?

Can I filter the data I retrieve?

Which AI clients can use this MCP?

How does the agent know which API endpoints to use?

Do I need an API key?

How do I find the right resource names?

What does browse_dataset return?

What is the difference between the catalog and the datasets?

CVM Dados Abertos AI Connector

IBAMA Dados Abertos AI Connector

Amsterdam Waste & Recycling AI Connector

Amsterdam City Status & Incidents AI Connector

Suggestions

Brasil.io AI Connector

Rijksmuseum AI Connector

Knoema AI Connector

NCDC Climate Data Online AI Connector