nhtsa-vehicle-safety-mcp-server

Nhtsa Search Recalls

nhtsa_search_recalls

Read-only

Search recall campaigns by vehicle or campaign number. Use for specific recall lookups, recall history for a vehicle, or looking up a known campaign number.

Input Schema

TableJSON Schema

Name	Required	Description
`make`	No	Vehicle manufacturer. Required with model and modelYear when not using campaignNumber.
`model`	No	Vehicle model. Required with make and modelYear.
`dateRange`	No	Filter recalls by received date. Applied locally since the API lacks native date filtering.
`modelYear`	No	Model year, a whole number. Required with make and model.
`campaignNumber`	No	NHTSA campaign number (e.g., "20V682000"). When provided, returns the campaign detail plus every vehicle it covers. Mutually exclusive with make/model/modelYear.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present when the call failed. Absent on success.
`notice`	No	Guidance when no recalls are found — e.g. how to verify make/model/year spelling.
`recalls`	No	Matching recall campaigns
`totalCount`	No	Total recalls matching criteria
`effectiveQuery`	No	The search key used: campaign number, or "make model modelYear" for vehicle queries.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedAug 21, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / anyOf

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "recalls",
+      "totalCount",
+      "effectiveQuery"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / error

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `mode_conflict`: Both campaignNumber and vehicle params were provided. `missing_required_combo`: Neither campaignNumber nor a complete vehicle triple was supplied. `campaign_not_found`: The campaignNumber did not match any NHTSA recall. `invalid_date`: A dateRange bound could not be parsed as a date. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "mode_conflict",
+            "missing_required_combo",
+            "campaign_not_found",
+            "invalid_date"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

removedOutput schema / required

Removed value: -[
-  "recalls",
-  "totalCount",
-  "effectiveQuery"
-]

Changed9 schema fields changedJul 30, 2026

changedInput schema / properties / campaignNumber / description

Previous value: -"NHTSA campaign number (e.g., \"20V682000\"). When provided, returns campaign details. Other params ignored."New value: +"NHTSA campaign number (e.g., \"20V682000\"). When provided, returns the campaign detail plus every vehicle it covers. Mutually exclusive with make/model/modelYear."

changedInput schema / properties / modelYear / description

Previous value: -"Model year. Required with make and model."New value: +"Model year, a whole number. Required with make and model."

addedInput schema / properties / modelYear / maximum
```
Added value: +9007199254740991
```
addedInput schema / properties / modelYear / minimum
```
Added value: +-9007199254740991
```
changedInput schema / properties / modelYear / type
```
Previous value: -"number"New value: +"integer"
```

addedOutput schema / properties / recalls / items / properties / affectedVehicles

Added value: +{
+  "description": "Every distinct make/model the campaign covers (campaign queries). Equipment and tire campaigns name the part here — make is the brand, model is the part — and carry no model year.",
+  "items": {
+    "additionalProperties": false,
+    "description": "One vehicle covered by the campaign",
+    "properties": {
+      "make": {
+        "description": "Vehicle make",
+        "type": "string"
+      },
+      "model": {
+        "description": "Vehicle model",
+        "type": "string"
+      },
+      "modelYear": {
+        "description": "Model year",
+        "type": "number"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / recalls / items / properties / investigationId

Added value: +{
+  "description": "ODI investigation that preceded this campaign, when NHTSA links one (campaign queries) — pass it as nhtsaId to nhtsa_search_investigations for the full record.",
+  "type": "string"
+}

changedOutput schema / properties / recalls / items / properties / reportReceivedDate / description
```
Previous value: -"Date received by NHTSA"New value: +"Date received by NHTSA (ISO YYYY-MM-DD)"
```

removedOutput schema / properties / recalls / items / properties / subject

Removed value: -{
-  "description": "Recall subject (campaign queries)",
-  "type": "string"
-}

Changed3 schema fields changedMay 30, 2026

addedOutput schema / properties / effectiveQuery

Added value: +{
+  "description": "The search key used: campaign number, or \"make model modelYear\" for vehicle queries.",
+  "type": "string"
+}

addedOutput schema / properties / notice

Added value: +{
+  "description": "Guidance when no recalls are found — e.g. how to verify make/model/year spelling.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "recalls",
-  "totalCount"
-]New value: +[
+  "recalls",
+  "totalCount",
+  "effectiveQuery"
+]

Changed1 schema field changedApr 24, 2026
- addedOutput schema / properties / recalls / items / description
```
Added value: +"A single recall campaign"
```
First observedApr 13, 2026

TDQS

A4/5.0

Behavior3/5

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

readOnlyHint=true already covers the non-mutating safety profile, so the description does not contradict annotations. However, the description itself adds little behavioral detail beyond the obvious search semantics, such as return behavior, pagination, rate limits, or the local dateRange filtering; the schema notes the local filtering, but the top-level description does not.

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?

The description is two clean sentences, front-loading the core function first and then adding meaningful use-case context. Every phrase contributes useful information, and there is no redundancy or unnecessary jargon.

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?

The presence of a complete input schema and output schema reduces the burden on the description. It explains the main situations in which the tool should be used, and the schema handles the parameter details. A small gap remains because the description does not mention how dateRange is applied locally or how campaignNumber expands to vehicle coverage, but those are covered by schema text.

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%, with each parameter already explaining its role and constraints, including mutual exclusivity between campaignNumber and vehicle fields. The description phrase 'by vehicle or campaign number' adds a helpful framing but no additional types, requirements, or formats beyond what the schema contains.

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?

The description clearly identifies the resource (recall campaigns) and the operation (search), and enumerates the two entry points: vehicle details or campaign number. It is unmistakably different from sibling tools by name and content, which are about complaints, investigations, ratings, VIN decoding, and vehicle lookup.

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

Usage Guidelines4/5

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

The description gives explicit use cases: specific recall lookups, recall history for a vehicle, and known campaign number lookups. It does not explicitly say when not to use the tool or point to a specific alternative, so it falls just short of a 5, but enough context for most agents to choose correctly.

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

All nhtsa-vehicle-safety-mcp-server 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.