# NYC Open Data Explorer AI Agent Connect

> NYC Open Data Explorer MCP gives your AI client direct access to the city's entire public data catalog. You can search through 3,000+ datasets, inspect specific column metadata, and run filtered queries using SOQL. It works with any MCP-compatible client like Claude, Cursor, or Windsurf without needing your own API keys.

## Overview
- **Category:** data-analytics
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_mAEjDrv8HxIky2zc7dK9Ip3znh6k9dtZoZIaMrSc/ai-agent-connect
- **Tags:** new-york, nyc, open-data, socrata, soda, catalog, government-public-data

## Description

You no longer need to manually download CSVs or navigate complex web portals to find city information. This MCP acts as a direct interface to the Socrata SODA API used by the City of New York. Your agent can now browse the full catalog of 3,000+ datasets, ranging from 311 service requests to traffic patterns and building permits.

Instead of just looking at a static list, your AI can actively investigate. It can find the right dataset using keywords, check exactly which columns are available, and then pull specific rows using SOQL filters. If you need to know the scale of a dataset before running a heavy query, your agent can check the total row counts or get grouped statistics for specific columns. It's a way to turn the city's massive public data repository into a live, searchable knowledge base for your AI-driven analysis.

## Tools

### browse_dataset
Query specific rows from any NYC Open Data dataset using SOQL filters. You can use double quotes for string values and ISO format for dates.

### dataset_row_count
Get the exact total number of rows in a dataset. You can apply filters to get a count for a specific subset of data.

### dataset_stats
Retrieve row counts and grouped statistics for a dataset. This is useful for seeing the top-N values within a specific column.

### get_dataset_info
Fetch the metadata for a single dataset. Use this to find the exact column names and descriptions before running queries.

### search_datasets
Search the entire NYC Open Data catalog using keywords. It returns the dataset ID, name, and description for each match.

## Prompt Examples

**Prompt:** 
```
Which NYC datasets are about potholes?
```

**Response:** 
```
search_datasets("potholes") returns the matching datasets like DOT Pothole Work Orders and 311 Street Condition requests with their IDs.
```

**Prompt:** 
```
What columns does the 311 service requests dataset have?
```

**Response:** 
```
get_dataset_info("erm2-nwe9") provides the full column list including complaint_type, descriptor, borough, and incident_address.
```

**Prompt:** 
```
How big is the 311 dataset and what are the top complaint types?
```

**Response:** 
```
dataset_row_count("erm2-nwe9") shows the total rows, while dataset_stats with a group_by on complaint_type shows the most frequent complaints.
```

## Capabilities

### Catalog Discovery
Your agent searches through 3,000+ datasets to find relevant information using keywords.

### Metadata Inspection
The AI checks column names and descriptions to ensure queries are formatted correctly.

### Filtered Row Retrieval
Your agent pulls specific data points using SOQL syntax for precise filtering.

### Data Aggregation
The AI calculates row counts and grouped statistics to summarize large datasets.

## Use Cases

### Real-time Trend Analysis
An analyst asks the AI to find the most recent 311 complaints in a specific borough.

### Dataset Auditing
A researcher checks the last update time and row counts to verify data freshness.

### Automated Reporting
An agent pulls grouped statistics on traffic patterns to populate a report.

### Schema Discovery
A developer uses the MCP to find the exact column names needed for a custom query.

## Benefits

- Eliminates the need for manual API key management or local data downloads.
- Provides direct access to the official Socrata SODA API used by NYC.
- Allows for precise data filtering using standard SOQL syntax.
- Enables rapid dataset discovery through keyword searching.

## How It Works

Connect your client to Vinkius and start querying NYC data immediately.

1. Connect your MCP-compatible client to the Vinkius platform.
2. Ask your AI client to find a specific dataset using keywords.
3. Use the dataset ID to inspect the available columns.
4. Run a filtered query to pull the specific rows you need.

## Frequently Asked Questions

**Do I need an API key to use this MCP?**
No. All access is anonymous and requires no credentials or API keys.

**How do I know which columns to query?**
You should use the get_dataset_info tool first to see the exact column names and descriptions.

**What happens if I want to filter by a specific borough?**
You can use the browse_dataset tool with a SOQL filter, such as borough="QUEENS".

**Can I get a summary of the data without downloading it?**
Yes, you can use dataset_stats to get grouped counts or dataset_row_count for total totals.

**Which AI clients can use this?**
Any MCP-compatible client like Claude, Cursor, or Windsurf can use this MCP once connected via Vinkius.

**Do I need an API key?**
No. NYC Open Data serves all public datasets anonymously over its SODA API (data.cityofnewyork.us). This MCP defines no credentials and needs nothing configured.

**How do I find the id of a dataset?**
Use search_datasets with a keyword — it queries the platform catalog and returns each match's 8-character id (like "erm2-nwe9"). That id feeds get_dataset_info, browse_dataset, dataset_stats and dataset_row_count.

**Borough values differ across datasets — how do I know the format?**
Formats are dataset-specific: 311 and shootings use UPPERCASE ("QUEENS"), food and sanitation use Title Case ("Queens"), DOT potholes use single-letter codes. Tool descriptions state the expected values, and the errors from a mismatched value are reported verbatim by the platform.

**What size is the catalog?**
The platform catalogs about 3,000 entries: roughly 2,400 standard datasets, plus filtered views, maps and external data sources. search_datasets searches all of them; the ny-* suite MCPs wrap the most-used families with dedicated tools.