DoorProfit Crime & Neighborhood Data

Get Crime Data & Safety Score

get_crime_data

Read-onlyIdempotent

Crime safety grade and nearby incident counts for one US address or coordinate pair. Returns a letter score (A+ safest through F), a short description of that grade, and — in cities where police publish incident data — counts by crime type within 1000ft for the same period the grade was built from (date_from/date_to; this varies by city and is not a live feed). incidents is null where we do not have incident data; a count of 0 means none were reported in that period. There is no national-average breakdown and no list of individual incidents. Use this for "is this address/neighborhood safe?" questions. Do NOT use it for demographics, income, rent or schools (use get_neighborhood_data) or for registered offenders (use search_offenders) — neither is included here. Pass either address or lat+lng, not both. US locations only; requires a DoorProfit API key and consumes 1 call from that key's quota, except for the free test address "500 Main St, Dallas, TX 75202".

Input Schema

TableJSON Schema

Name	Required	Description
`lat`	No	Latitude (use together with lng, as an alternative to address).
`lng`	No	Longitude (use together with lat, as an alternative to address).
`address`	No	Full US street address, e.g. "500 Adams St, Tulsa, OK". Provide either address OR lat+lng.

Output Schema

TableJSON Schema

Name	Required	Description
`success`	Yes
`location`	No	The resolved location for the query.
`incidents`	No	Incident counts within radius_feet for date_from through date_to. Null when this city does not publish incident data.
`test_mode`	No	True when querying the free test address.
`crime_score`	No	Letter safety grade from A+ (safest) to F.
`crime_numeric`	No	0-1 scale where 1 is safest.
`crime_description`	No	Human-readable explanation of the score.
`crime_score_source`	No	"incidents" when the grade comes from reported incidents on that block, "block_group" otherwise.

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedSep 29, 2026

removedOutput schema / properties / crime_breakdown

Removed value: -{
-  "additionalProperties": true,
-  "description": "Per-crime-type comparison vs the national average (e.g. assault, burglary, theft).",
-  "type": [
-    "object",
-    "null"
-  ]
-}

addedOutput schema / properties / crime_score_source

Added value: +{
+  "description": "\"incidents\" when the grade comes from reported incidents on that block, \"block_group\" otherwise.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / incidents / additionalProperties
```
Previous value: -trueNew value: +false
```

changedOutput schema / properties / incidents / description

Previous value: -"Recent crime incidents near the location."New value: +"Incident counts within radius_feet for date_from through date_to. Null when this city does not publish incident data."

addedOutput schema / properties / incidents / properties / by_type

Added value: +{
+  "additionalProperties": false,
+  "description": "Counts for the 12 types the grade uses. Every key is present; 0 means none reported.",
+  "properties": {
+    "arson": {
+      "type": "integer"
+    },
+    "assault": {
+      "type": "integer"
+    },
+    "burglary": {
+      "type": "integer"
+    },
+    "drug_offense": {
+      "type": "integer"
+    },
+    "kidnapping": {
+      "type": "integer"
+    },
+    "murder": {
+      "type": "integer"
+    },
+    "robbery": {
+      "type": "integer"
+    },
+    "sexual_offense": {
+      "type": "integer"
+    },
+    "shooting": {
+      "type": "integer"
+    },
+    "theft": {
+      "type": "integer"
+    },
+    "vandalism": {
+      "type": "integer"
+    },
+    "weapons": {
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / incidents / properties / count / description
```
Added value: +"Sum of by_type."
```

removedOutput schema / properties / incidents / properties / data

Removed value: -{
-  "items": {
-    "additionalProperties": true,
-    "properties": {
-      "address": {
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "date": {
-        "description": "YYYY-MM-DD.",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "distance_feet": {
-        "type": [
-          "integer",
-          "null"
-        ]
-      },
-      "lat": {
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "lng": {
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "type": {
-        "description": "Crime type.",
-        "type": [
-          "string",
-          "null"
-        ]
-      }
-    },
-    "type": "object"
-  },
-  "type": "array"
-}

addedOutput schema / properties / incidents / properties / date_from / description
```
Added value: +"YYYY-MM-DD start of the city scoring period."
```
addedOutput schema / properties / incidents / properties / date_to / description
```
Added value: +"YYYY-MM-DD end of the city scoring period."
```

changedOutput schema / properties / incidents / type

Previous value: -"object"New value: +[
+  "object",
+  "null"
+]

First observedJun 11, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/openWorld/non-destructive, but the description adds material context beyond them: that data is not a live feed, that incidents is null vs. 0 semantics, that incidents only exist in some cities, that a DoorProfit API key is required consuming 1 quota call, and a free test address. This is unusually rich behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: the core purpose and return shape come first, then caveats, then usage routing, then constraints. Every clause carries information, though the single long paragraph could be split for scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present the description needn't describe return values, yet it clarifies the grade scale, null-vs-zero semantics, and coverage limits — exactly the ambiguities an agent would otherwise guess at. Nothing needed to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds a real constraint not in the schema: 'Pass either address or lat+lng, not both.' That mutual-exclusivity rule is genuine value beyond the structured fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Crime safety grade and nearby incident counts') and scopes it to 'one US address or coordinate pair.' It also explicitly names what it is not (neighborhood data, offenders), so an agent can separate it from siblings without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit use case ('is this address/neighborhood safe?' questions) plus two named exclusions routing to alternatives: get_neighborhood_data for demographics/income/rent/schools and search_offenders for registered offenders. When-to-use and when-not-to-use are both covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All DoorProfit Crime & Neighborhood Data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?