# Crime Data API (US cities)

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

- name: io.github.shaharfrish6/crime-data-api
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 75/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.shaharfrish6%2Fcrime-data-api
- tools: https://api.protogrid.dev/v1/servers/io.github.shaharfrish6%2Fcrime-data-api/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 45
- drivers: +website +reachable +uptime-100% +updated-5d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 75 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: crime_score (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); crime_stats (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); crime_incidents (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 910 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`, `stability.new_links`: tool history recorded for 5 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 910 tokens to load them all
- tool set hash: 6c134c66dd227e9fac738e70d3ab0eb0
- tools last changed: 2026-11-11T01:43:14.180Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.shaharfrish6/crime-data-api.svg)](https://protogrid.dev/servers/io.github.shaharfrish6/crime-data-api)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-11 `crime_coverage` added
  - Covered cities, data source, licence and freshness.
- 2026-11-11 `crime_score` added
  - Safety score 0-100 (higher = fewer incidents) and A-F grade for a point: incident density percentile against sampled occupied-area cells of the city (same radius) over its last 12 months. Not a prediction of personal risk; not comparable across cities. Outside covered cities it returns coverage "city_fallback": the city's FBI city-wide violent/property rates per 100k and national percentiles, no grade. May include a "tract" block: 2020 Census tract population and incidents per 1,000 estimated residents in the radius per year (tract residents only, so commercial and nightlife areas overstate risk).
- 2026-11-11 `crime_compare` added
  - Compare incident stats (by category, violent vs property, hour, weekday, 90-day trend) for 2-5 points with the same radius.
- 2026-11-11 `crime_stats` added
  - Incident counts by category and by month near a point.
- 2026-11-11 `crime_incidents` added
  - Recent police-reported incidents near a point in covered US cities, newest first.
- 2026-11-10 `crime_score` removed
  - Safety score 0-100 (higher = fewer incidents) and A-F grade for a point: incident density percentile against sampled occupied-area cells of the city (same radius) over its last 12 months. Not a prediction of personal risk; not comparable across cities. Outside covered cities it returns coverage "city_fallback": the city's FBI city-wide violent/property rates per 100k and national percentiles, no grade. May include a "tract" block: 2020 Census tract population and incidents per 1,000 estimated residents in the radius per year (tract residents only, so commercial and nightlife areas overstate risk).
- 2026-11-10 `crime_compare` removed
  - Compare incident stats (by category, violent vs property, hour, weekday, 90-day trend) for 2-5 points with the same radius.
- 2026-11-10 `crime_stats` removed
  - Incident counts by category and by month near a point.
- 2026-11-10 `crime_incidents` removed
  - Recent police-reported incidents near a point in covered US cities, newest first.
- 2026-11-10 `crime_coverage` removed
  - Covered cities, data source, licence and freshness.

Full history: https://api.protogrid.dev/v1/servers/io.github.shaharfrish6%2Fcrime-data-api/changes

## Remotes

- https://crimedata.dev/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (5)

- `crime_compare`: Compare incident stats (by category, violent vs property, hour, weekday, 90-day trend) for 2-5 points with the same radius.
- `crime_coverage`: Covered cities, data source, licence and freshness.
- `crime_incidents`: Recent police-reported incidents near a point in covered US cities, newest first.
- `crime_score`: Safety score 0-100 (higher = fewer incidents) and A-F grade for a point: incident density percentile against sampled occupied-area cells of the city (same radius) over its last 12 months. Not a prediction of personal risk; not comparable across cities. Outside covered cities it returns coverage "city_fallback": the city's FBI city-wide violent/property rates per 100k and national percentiles, no grade. May include a "tract" block: 2020 Census tract population and incidents per 1,000 estimated residents in the radius per year (tract residents only, so commercial and nightlife areas overstate risk).
- `crime_stats`: Incident counts by category and by month near a point.