nhtsa-vehicle-safety-mcp-server

Nhtsa Search Investigations

nhtsa_search_investigations

Read-only

Search NHTSA defect investigations from the ODI flat file — covering Preliminary Evaluations (PE), Engineering Analyses (EA), Defect Petitions (DP), Recall Queries (RQ), Audit Queries (AQ), and additional ODI types. make, model, and component are structured filters against the investigation record's vehicle associations. All filters are ANDed. Use nhtsaId to fetch one investigation by its exact ID — including the investigationId nhtsa_search_recalls returns for a campaign. Investigations may link to a resulting recall campaign via recallCampaign.

Input Schema

TableJSON Schema

Name	Required	Description
`make`	No	Structured filter — matches against the investigation's associated vehicle makes (e.g., "TOYOTA"). ANDed with other filters.
`limit`	No	Max investigations to return. Defaults to 20; max 25. The cap is lower than the other paginated tools because a single investigation summary can run several thousand characters and is rendered in full.
`model`	No	Structured filter — matches against the investigation's associated vehicle models. ANDed with other filters.
`query`	No	Free-text search across investigation ID, subject, and summary.
`offset`	No	Pagination offset into the matching investigations. Defaults to 0.
`status`	No	Filter by status: "O" (Open) or "C" (Closed). Omit to include both.
`nhtsaId`	No	Exact NHTSA investigation ID (e.g. "EA23003"), case-insensitive. Fetches that one record — mutually exclusive with every other filter.
`component`	No	Structured filter — matches against the investigation's affected components (e.g., "STEERING"). ANDed with other filters.
`investigationType`	No	Filter by ODI investigation type code (the leading letters of the NHTSA ID). Named types: "PE" (Preliminary Evaluation), "EA" (Engineering Analysis), "DP" (Defect Petition), "RQ" (Recall Query), "AQ" (Audit Query). Additional valid codes present in the dataset: "SQ", "EQ", "RP", "ID", "TA", "C". Pass any code exactly as it appears in the investigation ID prefix.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present when the call failed. Absent on success.
`limit`	No	Pagination limit used for this page
`notice`	No	Guidance when no investigations match the filters, or when the requested page overshoots the result set.
`offset`	No	Pagination offset used for this page
`returned`	No	Number of investigations in this page
`totalCount`	No	Total matching investigations
`effectiveQuery`	No	Applied filters as a readable string, e.g. make="Ford" status="O".
`investigations`	No	Matching investigations

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": [
+      "totalCount",
+      "returned",
+      "offset",
+      "limit",
+      "investigations",
+      "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`: nhtsaId was combined with another filter. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "mode_conflict"
+          ],
+          "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: -[
-  "totalCount",
-  "returned",
-  "offset",
-  "limit",
-  "investigations",
-  "effectiveQuery"
-]

Changed1 schema field changedJul 30, 2026

changedOutput schema / properties / notice / description

Previous value: -"Guidance when no investigations match — e.g. suggestions for broadening the search."New value: +"Guidance when no investigations match the filters, or when the requested page overshoots the result set."

Changed2 schema fields changedJul 30, 2026

addedInput schema / properties / nhtsaId

Added value: +{
+  "description": "Exact NHTSA investigation ID (e.g. \"EA23003\"), case-insensitive. Fetches that one record — mutually exclusive with every other filter.",
+  "type": "string"
+}

changedInput schema / properties / query / description

Previous value: -"Free-text search across investigation subject and summary."New value: +"Free-text search across investigation ID, subject, and summary."

Changed14 schema fields changedJul 30, 2026

changedInput schema / properties / limit / description

Previous value: -"Max results to return. Default: 20."New value: +"Max investigations to return. Defaults to 20; max 25. The cap is lower than the other paginated tools because a single investigation summary can run several thousand characters and is rendered in full."

addedInput schema / properties / limit / maximum
```
Added value: +25
```
addedInput schema / properties / limit / minimum
```
Added value: +1
```

changedInput schema / properties / limit / type

Previous value: -"number"New value: +"integer"

changedInput schema / properties / offset / description

Previous value: -"Pagination offset. Default: 0."New value: +"Pagination offset into the matching investigations. Defaults to 0."

addedInput schema / properties / offset / maximum
```
Added value: +9007199254740991
```
addedInput schema / properties / offset / minimum
```
Added value: +0
```

changedInput schema / properties / offset / type

Previous value: -"number"New value: +"integer"

changedInput schema / properties / status / description

Previous value: -"Filter by status: \"O\" (Open), \"C\" (Closed)."New value: +"Filter by status: \"O\" (Open) or \"C\" (Closed). Omit to include both."

addedInput schema / properties / status / enum
```
Added value: +[
+  "O",
+  "C"
+]
```

addedOutput schema / properties / limit

Added value: +{
+  "description": "Pagination limit used for this page",
+  "type": "number"
+}

addedOutput schema / properties / offset

Added value: +{
+  "description": "Pagination offset used for this page",
+  "type": "number"
+}

addedOutput schema / properties / returned

Added value: +{
+  "description": "Number of investigations in this page",
+  "type": "number"
+}

changedOutput schema / required

Previous value: -[
-  "totalCount",
-  "investigations",
-  "effectiveQuery"
-]New value: +[
+  "totalCount",
+  "returned",
+  "offset",
+  "limit",
+  "investigations",
+  "effectiveQuery"
+]

Changed1 schema field changedJun 2, 2026

changedInput schema / properties / investigationType / description

Previous value: -"Filter by type: \"PE\" (Preliminary Evaluation), \"EA\" (Engineering Analysis), \"DP\" (Defect Petition), \"RQ\" (Recall Query)."New value: +"Filter by ODI investigation type code (the leading letters of the NHTSA ID). Named types: \"PE\" (Preliminary Evaluation), \"EA\" (Engineering Analysis), \"DP\" (Defect Petition), \"RQ\" (Recall Query), \"AQ\" (Audit Query). Additional valid codes present in the dataset: \"SQ\", \"EQ\", \"RP\", \"ID\", \"TA\", \"C\". Pass any code exactly as it appears in the investigation ID prefix."

Changed15 schema fields changedMay 30, 2026

addedInput schema / properties / component

Added value: +{
+  "description": "Structured filter — matches against the investigation's affected components (e.g., \"STEERING\"). ANDed with other filters.",
+  "type": "string"
+}

changedInput schema / properties / make / description

Previous value: -"Free-text filter — matches manufacturer name against subject/description text. ANDed with other filters."New value: +"Structured filter — matches against the investigation's associated vehicle makes (e.g., \"TOYOTA\"). ANDed with other filters."

changedInput schema / properties / model / description

Previous value: -"Free-text filter — matches model name against subject/description text. ANDed with other filters."New value: +"Structured filter — matches against the investigation's associated vehicle models. ANDed with other filters."

changedInput schema / properties / query / description

Previous value: -"Free-text search across investigation subjects and descriptions."New value: +"Free-text search across investigation subject and summary."

addedOutput schema / properties / investigations / items / properties / closeDate

Added value: +{
+  "description": "Date investigation closed (YYYY-MM-DD), if closed",
+  "type": "string"
+}

addedOutput schema / properties / investigations / items / properties / components

Added value: +{
+  "description": "Affected components",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

removedOutput schema / properties / investigations / items / properties / description

Removed value: -{
-  "description": "Investigation description (HTML stripped)",
-  "type": "string"
-}

removedOutput schema / properties / investigations / items / properties / latestActivityDate
```
Removed value: -{
-  "description": "Date of latest activity",
-  "type": "string"
-}
```

addedOutput schema / properties / investigations / items / properties / makes

Added value: +{
+  "description": "Associated vehicle makes",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / investigations / items / properties / manufacturer
```
Added value: +{
+  "description": "Manufacturer name",
+  "type": "string"
+}
```

addedOutput schema / properties / investigations / items / properties / models

Added value: +{
+  "description": "Associated vehicle models",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / properties / investigations / items / properties / openDate / description

Previous value: -"Date investigation opened"New value: +"Date investigation opened (YYYY-MM-DD)"

addedOutput schema / properties / investigations / items / properties / recallCampaign

Added value: +{
+  "description": "Linked recall campaign number (if any) — use with nhtsa_search_recalls",
+  "type": "string"
+}

addedOutput schema / properties / investigations / items / properties / summary

Added value: +{
+  "description": "Investigation summary",
+  "type": "string"
+}

addedOutput schema / properties / investigations / items / properties / years

Added value: +{
+  "description": "Associated model years",
+  "items": {
+    "type": "number"
+  },
+  "type": "array"
+}

Changed4 schema fields changedMay 30, 2026

addedOutput schema / properties / effectiveQuery

Added value: +{
+  "description": "Applied filters as a readable string, e.g. make=\"Ford\" status=\"O\".",
+  "type": "string"
+}

removedOutput schema / properties / message

Removed value: -{
-  "description": "Contextual guidance populated when no investigations match the filters",
-  "type": "string"
-}

addedOutput schema / properties / notice

Added value: +{
+  "description": "Guidance when no investigations match — e.g. suggestions for broadening the search.",
+  "type": "string"
+}

changedOutput schema / required

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

Changed1 schema field changedApr 24, 2026
- addedOutput schema / properties / investigations / items / description
```
Added value: +"A single NHTSA investigation"
```

Changed3 schema fields changedApr 23, 2026

removedOutput schema / properties / total

Removed value: -{
-  "description": "Total matching investigations",
-  "type": "number"
-}

addedOutput schema / properties / totalCount

Added value: +{
+  "description": "Total matching investigations",
+  "type": "number"
+}

changedOutput schema / required

Previous value: -[
-  "total",
-  "investigations"
-]New value: +[
+  "totalCount",
+  "investigations"
+]

Changed1 schema field changedApr 19, 2026

addedOutput schema / properties / message

Added value: +{
+  "description": "Contextual guidance populated when no investigations match the filters",
+  "type": "string"
+}

First observedApr 13, 2026

TDQS

A4.3/5.0

Behavior4/5

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

The readOnlyHint annotation already signals safety, and the description adds valuable behavior details such as pagination (`offset`, `limit`) and the mutual exclusivity of `nhtsaId` with other filters, plus the case-insensitive fetching of a single record. This goes beyond the annotation without contradicting it.

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 dense but every sentence contributes: purpose, filter types, mutual exclusivity, and pagination details. It is well-structured, front-loaded with the core purpose, and avoids redundancy or filler.

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?

The description fully equips a user to call the tool: it covers all filters, explains mutual exclusivity, pagination behavior, investigation type codes, and the single-record fetch mode. Since an output schema exists, return values need not be described. No critical usage gaps remain.

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?

All nine parameters have schema descriptions (100% coverage), and the description adds extra semantics beyond those: `nhtsaId` is case-insensitive and mutually exclusive, `investigationType` explains the leading-letter prefix and lists additional valid codes, and `query` covers specific fields. This enriches parameter understanding beyond the raw schema.

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 states the tool searches NHTSA defect investigations from the ODI flat file, listing coverage of specific investigation types (PE, EA, DP, RQ, AQ, and additional types). It uses a specific verb and resource, making its intent unambiguous and distinct from sibling tools like recalls or complaints.

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?

The description explains the tool's scope and filter behavior but does not explicitly mention when to use it over sibling tools (e.g., search_recalls) or provide exclusions. While the coverage types imply a focused use case, explicit guidance on alternatives is missing.

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.

Nhtsa Search Investigations

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources