Skip to content

Crime Data API (US cities) MCP server

io.github.shaharfrish6/crime-data-apishaharfrish6streamable-httpv1.0.0Scanned

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

5 tools: 2 do something that can't be undone, 2 change things and 1 only read.

Tools: 0 delete, 2 irreversible, 2 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Crime Data API (US cities) MCP server can do

The Crime Data API (US cities) MCP server is published by the GitHub account shaharfrish6. It has 5 tools. It can do things that cannot be undone, such as sending, paying or publishing (crime_incidents and crime_stats) and create or change data (2 tools: crime_score and crime_coverage), but cannot delete data. 1 tool only reads.

2 tools can send data out of your system (crime_incidents and crime_stats).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 8, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

5 tools

Can't be undone 2Claude Code: ask
  • crime_incidentsRecent police-reported incidents near a point in covered US cities, newest first.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Recent police-reported incidents near a point in covered US cities, newest first.
  • crime_statsIncident counts by category and by month near a point.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Incident counts by category and by month near a point.
Changes things 2Claude Code: ask
  • crime_coverageCovered cities, data source, licence and freshness.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Covered cities, data source, licence and freshness.
  • crime_scoreSafety 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 …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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).
Only reads 1Show 1 read-only tool
  • crime_compareCompare incident stats (by category, violent vs property, hour, weekday, 90-day trend) for 2-5 points with the same radius.No findings

    Why it is in this group

    • The name "crime_compare" says "compare": a word for reading.
    Description, as the server wrote it
    Compare incident stats (by category, violent vs property, hour, weekday, 90-day trend) for 2-5 points with the same radius.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 16, 2026, 14:21 UTC, unchanged since Nov 9, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (2 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://crimedata.dev/mcp: tools/list returned 5 tools to an anonymous client, including crime_incidents (irreversible), crime_stats (irreversible), crime_score (write), crime_coverage (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__crime-data-api__crime_compare"
    ],
    "ask": [
      "mcp__crime-data-api__crime_incidents",
      "mcp__crime-data-api__crime_stats",
      "mcp__crime-data-api__crime_score",
      "mcp__crime-data-api__crime_coverage"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as crime-data-api. Review it before you use it.

Capability tags behind 2 rules
  • mcp__crime-data-api__crime_incidents outbound
  • mcp__crime-data-api__crime_stats outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.shaharfrish6/crime-data-api/verify?hash=332d1ff87cdb7bd07383c2394f20dfaa3685dafeed11d4ccde1943e379c0d0e2" | jq -e '.changed == false'

Pinned hash 332d1ff87cdb, from Nov 8, 2026, 21:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.shaharfrish6/crime-data-api/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.shaharfrish6/crime-data-api
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.shaharfrish6/crime-data-api.svg)](https://radar.anlyon.com/servers/io.github.shaharfrish6/crime-data-api)

Source: MCP Registry. Synced Nov 8, 2026, 21:18 UTC.

Crime Data API (US cities) MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Crime Data API (US cities) MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Crime Data API (US cities) MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Crime Data API (US cities) MCP server do things that cannot be undone?

Yes. 2 tools can send, pay, publish or merge: crime_incidents and crime_stats.

What tools does the Crime Data API (US cities) MCP server have?

5 tools: 2 irreversible, 2 write, 1 read. crime_incidents, crime_stats, crime_score, crime_coverage and crime_compare.

Does the Crime Data API (US cities) MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Crime Data API (US cities) MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): crime_incidents and crime_stats.

Has the Crime Data API (US cities) MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.