usda-mcp-server

Search USDA Foods

usda_search_foods

Read-only

Search USDA FoodData Central foods by keyword. Returns matching foods with FDC IDs and a preview of key nutrients (energy, protein, fat, carbs — not guaranteed complete). Use the returned fdcId with usda_get_food for the full nutrient profile, or usda_compare_foods for side-by-side comparisons. When dataType is omitted, defaults to SR Legacy (common whole foods with complete profiles) — or to Branded when brandOwner is set, since only Branded records carry one. Set dataType to ["Branded"] for packaged products, or include a UPC/GTIN code as the query. Pass brandOwner (e.g. "General Mills") to narrow branded results.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	Search terms — food name, ingredient, or UPC/GTIN code for branded products. Examples: "chicken breast raw", "banana", "012345678901".
`dataType`	No	FDC data sources to search. Omitting this defaults to ["SR Legacy"] (common whole foods, complete nutrient profiles), or to ["Branded"] when brandOwner is set. Include "Branded" for packaged products. Multiple values allowed.
`pageSize`	No	Number of results per page. Default 10, maximum 50.
`brandOwner`	No	Filter branded results by brand owner name (e.g. "General Mills", "Kraft"). Only Branded records carry one, so setting this defaults dataType to ["Branded"] unless dataType is given explicitly.
`pageNumber`	No	Page number (1-based). Use with totalPages to paginate.
`foodCategory`	No	Filter by USDA food category (e.g. "Poultry Products", "Vegetables and Vegetable Products"). Case-sensitive.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present when the call failed. Absent on success.
`foods`	No	Foods matching the search query.
`totalHits`	No	Total number of foods matching the query across all pages.
`totalCount`	No	Total foods matching the query across all pages.
`totalPages`	No	Total number of pages available.
`currentPage`	No	Current page number (1-based).

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedAug 25, 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": [
+      "totalHits",
+      "currentPage",
+      "totalPages",
+      "foods",
+      "totalCount"
+    ]
+  },
+  {
+    "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: `query_empty`: The query is empty or contains only whitespace. `no_results`: No foods matched the query in the specified data sources. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "query_empty",
+            "no_results"
+          ],
+          "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: -[
-  "totalHits",
-  "currentPage",
-  "totalPages",
-  "foods",
-  "totalCount"
-]

First observedAug 13, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description is consistent with them (no contradiction). It adds valuable behavior beyond annotations: it warns that the nutrient preview is 'not guaranteed complete,' explains the default dataType logic (SR Legacy vs Branded based on brandOwner), and notes that only Branded records carry a brandOwner. This transparency about data completeness and default behavior exceeds what annotations alone provide.

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?

The description is dense with information but not bloated. It front-loads the core purpose and return value, then moves to downstream tool usage and defaults. Each sentence contributes new guidance. Slightly long but efficient; a score of 4 reflects that it could be slightly tightened without losing essential details.

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?

Given the output schema exists and the description already notes the returned nutrient preview (energy, protein, fat, carbs) and FDC IDs, an agent has enough to understand the call result. The description also covers defaults and edge cases (UPC codes, brandOwner) that are not evident from the schema alone. Nothing needed for correct invocation 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 description coverage is 100%, so the baseline is 3. The description adds meaningful enhancements: it explains how the query parameter can also accept UPC/GTIN codes, and it details the interaction between dataType and brandOwner (that setting brandOwner defaults dataType to ['Branded'] unless explicitly overridden). This goes beyond the schema's static field descriptions, justifying a score above baseline.

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 states a specific verb ('Search'), a precise resource ('USDA FoodData Central foods'), and the input ('by keyword'). It also explains what is returned (matching foods with FDC IDs and a nutrient preview), and explicitly distinguishes itself from sibling tools by naming usda_get_food and usda_compare_foods as follow-ups. This fully establishes the tool's unique role.

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?

The description provides explicit routing: 'Use the returned fdcId with usda_get_food for the full nutrient profile, or usda_compare_foods for side-by-side comparisons.' It also clarifies when to set dataType to ['Branded'] and how to use UPC/GTIN codes or brandOwner filters. These guidelines directly address selection against alternative tools and appropriate usage contexts, leaving no ambiguity.

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

All usda-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.