CityAlert

Get live incidents

get_incidents

Read-onlyIdempotent

Merged live incidents from all feeds plus manual reports. Filter by region key, category, group, severity, source, or bbox. Results come from a shared ~15-minute snapshot; real-time refresh requires an API key with that entitlement (details: cityalert.live/developers).

Input Schema

Name	Required	Description
`q`	No	Case-insensitive substring match on type/title/neighbourhood
`bbox`	No	[minLon, minLat, maxLon, maxLat]
`limit`	No	Max incidents to return (default 50)
`detail`	No	Response detail. 'full' (default): every field incl. description, neighbourhood and reporter/vote metadata. 'compact': id/type/title/coords/time/severity/url only — about half the tokens, for list-style answers.
`groups`	No	Normalized subtypes to include, e.g. ['violent','property','collision','wildfire']. See group keys in the /api/incidents OpenAPI doc.
`region`	No	Focus-region key, e.g. 'vancouver' (see list_regions)
`source`	No	Feed source, e.g. 'usgs', 'gdacs', 'eccc', 'vpd', 'bcws', 'vernon-media', 'manual'
`refresh`	No	Re-fetch upstream feeds instead of returning the shared ~15-minute snapshot. Only honored for API keys with real-time entitlement; ignored otherwise.
`category`	No	Incident category
`minSeverity`	No	Minimum severity (low < medium < high < critical)

Output Schema

Name	Required	Description	Default
`feeds`	Yes
`total`	Yes
`region`	No
`delayed`	No
`returned`	Yes
`incidents`	Yes
`delayMinutes`	No
`textTruncated`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 10, 2026

changedInput schema / properties / bbox / items

Previous value: -falseNew value: +{
+  "type": "number"
+}

removedInput schema / properties / bbox / prefixItems

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "number"
-  },
-  {
-    "type": "number"
-  },
-  {
-    "type": "number"
-  }
-]

addedInput schema / properties / detail

Added value: +{
+  "description": "Response detail. 'full' (default): every field incl. description, neighbourhood and reporter/vote metadata. 'compact': id/type/title/coords/time/severity/url only — about half the tokens, for list-style answers.",
+  "enum": [
+    "compact",
+    "full"
+  ],
+  "type": "string"
+}

changedInput schema / properties / limit / description

Previous value: -"Max incidents to return (default 250)"New value: +"Max incidents to return (default 50)"

changedInput schema / properties / refresh / description

Previous value: -"Bypass the feed cache and re-fetch sources"New value: +"Re-fetch upstream feeds instead of returning the shared ~15-minute snapshot. Only honored for API keys with real-time entitlement; ignored otherwise."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "delayMinutes": {
+      "type": "number"
+    },
+    "delayed": {
+      "type": "boolean"
+    },
+    "feeds": {
+      "additionalProperties": false,
+      "properties": {
+        "count": {
+          "type": "number"
+        },
+        "failed": {
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "error": {
+                "type": "string"
+              },
+              "source": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "source"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "required": [
+        "count",
+        "failed"
+      ],
+      "type": "object"
+    },
+    "incidents": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "approximate": {
+            "type": "boolean"
+          },
+          "category": {
+            "type": "string"
+          },
+          "confirms": {
+            "type": "number"
+          },
+          "count": {
+            "type": "number"
+          },
+          "description": {
+            "type": "string"
+          },
+          "flags": {
+            "type": "number"
+          },
+          "group": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "lat": {
+            "type": "number"
+          },
+          "lon": {
+            "type": "number"
+          },
+          "nhood": {
+            "type": "string"
+          },
+          "region": {
+            "type": "string"
+          },
+          "reporter": {
+            "additionalProperties": false,
+            "properties": {
+              "confirmed": {
+                "type": "number"
+              },
+              "handle": {
+                "type": "string"
+              },
+              "reports": {
+                "type": "number"
+              },
+              "role": {
+                "anyOf": [
+                  {
+                    "enum": [
+                      "curator",
+                      "moderator"
+                    ],
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "required": [
+              "handle",
+              "role",
+              "reports",
+              "confirmed"
+            ],
+            "type": "object"
+          },
+          "resolves": {
+            "type": "number"
+          },
+          "severity": {
+            "type": "string"
+          },
+          "source": {
+            "type": "string"
+          },
+          "sources": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "status": {
+            "enum": [
+              "pending",
+              "active",
+              "resolved",
+              "hidden"
+            ],
+            "type": "string"
+          },
+          "time": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "type": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "source",
+          "category",
+          "type",
+          "title",
+          "lat",
+          "lon",
+          "time",
+          "severity"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "region": {
+      "type": "string"
+    },
+    "returned": {
+      "type": "number"
+    },
+    "textTruncated": {
+      "type": "string"
+    },
+    "total": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "total",
+    "returned",
+    "incidents",
+    "feeds"
+  ],
+  "type": "object"
+}

Changed1 schema field changedSep 23, 2026

changedInput schema / properties / category / enum

Previous value: -[
-  "crime",
-  "fire",
-  "disaster",
-  "weather",
-  "unrest",
-  "health",
-  "infra",
-  "report"
-]New value: +[
+  "crime",
+  "fire",
+  "disaster",
+  "weather",
+  "unrest",
+  "health",
+  "infra",
+  "alert",
+  "report"
+]

First observedSep 19, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description still adds genuinely new behavior: results come from a shared ~15-minute snapshot rather than live data, and real-time refresh requires an entitlement. That staleness/caching disclosure is exactly the kind of context an agent needs and is not in the annotations. It omits pagination/ordering behavior.

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

Conciseness5/5

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

Three tight sentences: identity/scope first, filter surface second, behavioral caveat last. No filler, and the most decision-relevant constraint (snapshot staleness) is stated before the pointer to developer docs.

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

Completeness4/5

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

With 10 optional params, full schema coverage, rich annotations, and an output schema, the description carries the necessary extra context: merged provenance and snapshot freshness. Only minor gaps remain (ordering, default/max limit behavior, dedup across feeds), which the output schema and param defaults largely cover.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents every parameter including bbox format, detail modes, and the refresh entitlement caveat. The description's filter list and entitlement note largely restate what the schema says. Baseline 3 is appropriate.

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

Purpose4/5

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

The description names the resource (live incidents) and adds meaningful scope beyond the tool name: merged from all feeds plus manual reports. That scope distinguishes it from get_news and get_crime_year, though it never explicitly names those siblings. Clear verb+resource with implicit differentiation.

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

Usage Guidelines3/5

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

It lists the filter dimensions (region, category, group, severity, source, bbox), which implies the intended use case is filtered incident retrieval, and it flags the ~15-minute snapshot / refresh-entitlement constraint. However, it never states when to choose this over get_news, get_crime_year, or get_trends, and gives no explicit exclusions.

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

All CityAlert 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?