Skip to content
MCP server

Crime Data API (US cities)

Police-reported incidents, stats, comparisons and safety scores for 11 US cities

Install
Pricing
Freemium
Platforms
API, Web
Runs
Remotely
Version
1.0.0
Listing updated
2 days ago

About Crime Data API (US cities)

Crime Data API (US cities) is a freemium MCP server for analytics and data. It runs as a hosted remote server, so there is nothing to install locally.

Coverage is limited to Baltimore, Boston, Cincinnati, Dallas, Kansas City, Milwaukee, Minneapolis, New York City, San Francisco, Seattle and Washington DC, drawn from each city's open data portal. The site counts 964,126 incident records in its latest snapshot, ingests each city nightly, and shows every city's licence and newest record date. New York City publishes quarterly, so its latest data is about three months old. Elsewhere in the US only city-wide FBI rates are available through the score endpoint.

The free MCP server needs no key and is capped at the last 180 days, a 1 km radius and 50 rows per call. Its five tools take an address instead of coordinates. The same data is available through a REST API with incident search, stats, two-to-five-point comparisons, and a 0 to 100 density score with an A to F grade.

The publisher says reports are not convictions or a prediction of personal risk, and the data is not for tenant, employment, credit or insurance screening.

Install

Run in a terminal

claude mcp add --transport http crime-data-api https://crimedata.dev/mcp

Add to Settings → Connectors → Add custom connector

https://crimedata.dev/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "crime-data-api": {
      "url": "https://crimedata.dev/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "crime-data-api": {
      "type": "http",
      "url": "https://crimedata.dev/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "crime-data-api": {
      "serverUrl": "https://crimedata.dev/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "crime-data-api": {
      "type": "http",
      "url": "https://crimedata.dev/mcp"
    }
  }
}

Tools this server provides (5)

Taken from the project documentation; the running server may differ.

crime_incidents
Searches police-reported incidents.
crime_stats
Returns incident statistics for an area.
crime_compare
Compares incident data across locations.
crime_score
Returns a safety score for a location.
crime_coverage
Reports coverage and data freshness by city.

What it does

Incident search
crime_incidents finds reports by location, radius, date and category such as theft, assault or burglary.
Area statistics
crime_stats summarises counts for an address or point.
Place comparison
crime_compare compares several locations within the covered cities.
Density score
crime_score gives an incident density score and grade, with an FBI city-wide fallback elsewhere.
Coverage check
crime_coverage shows cities, sources, licences and data freshness.
Keyless MCP access
The free MCP server needs no API key but limits range, radius and rows.

Good for

  • Check reported theft near an address in San Francisco
  • Compare incident density between two Seattle neighborhoods
  • Add a safety scorecard to a real-estate listing page
  • Verify how fresh a city's data is before citing it

Pricing

Freemium, from $29 a month

MCP free without a key; REST API Basic free with 500 calls/month, Pro $29/mo, Ultra $79/mo

Prices change. Check crimedata.dev before you buy.

Crime Data API (US cities) FAQ

Which cities are covered?

Baltimore, Boston, Cincinnati, Dallas, Kansas City, Milwaukee, Minneapolis, New York City, San Francisco, Seattle and Washington DC.

What limits apply to the free MCP server?

The last 180 days, a 1 km radius and 50 rows per call, with no key.

What does the API cost?

Basic is free with 500 calls a month; Pro is $29 a month for 20,000 calls and Ultra is $79 for 100,000.

Can I use it for tenant or employment screening?

No. The site says it is not a consumer reporting agency and the data is not for screening.

How fresh is the data?

Each city is ingested nightly, but source updates range from daily to quarterly for New York City.

Is Crime Data API (US cities) free?

Crime Data API (US cities) has a free plan, with paid plans for more usage or features. Paid plans start at $29 a month.

How do I add Crime Data API (US cities) to Claude Code?

Run this command in your terminal: claude mcp add --transport http crime-data-api https://crimedata.dev/mcp

What are the best alternatives to Crime Data API (US cities)?

The closest alternatives to Crime Data API (US cities) are REA, Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP and Agent Roast.

Alternatives to Crime Data API (US cities)

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data
  3. Hosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat

    • 8 tools
    • Remote
    • Freemium
    • 8.1K GitHub stars
    • Marketing and SEO
  4. Indian NSE and BSE stock market data for AI assistants through 48 MCP tools

    • 17 tools
    • Remote
    • Freemium
    • 150 GitHub stars
    • Finance and payments
  5. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  6. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases