usaspending-mcp-server

Search Award Recipients

usaspending_search_recipients

Read-onlyIdempotent

Search for organizations or individuals receiving federal funds by name, UEI (Unique Entity Identifier), or DUNS. Returns recipient hash IDs, UEI/DUNS identifiers, total award amounts, and hierarchy level. Results are paginated — use page to retrieve matches beyond the first page; page_metadata.total reports the full match count. Recipient hash IDs from this tool can be passed to usaspending_get_recipient for full profiles. Recipient level: P = parent organization, C = child entity, R = standalone.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	Page number (1-based) — request the next page to retrieve matches beyond the first
`limit`	No	Maximum results per page (1–100)
`keyword`	Yes	Name, UEI, DUNS, or keyword to search for — partial matches are supported
`award_type`	No	Filter by award type category to scope the total amounts returned

Output Schema

TableJSON Schema

Name	Required	Description
`page`	No	Current page number returned
`error`	No	Present when the call failed. Absent on success.
`notice`	No	Recovery hint — how to continue to the next page when more results exist, or how to broaden the search when empty. Absent when the full match set fits on this page.
`results`	No	Matching recipients
`has_next`	No	Whether there are more pages of results
`totalCount`	No	Total matching recipients across all pages
`page_metadata`	No	Pagination metadata — page through with the page input to reach later matches
`recipient_count`	No	Number of matching recipients returned on this page

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": [
+      "results",
+      "page_metadata",
+      "recipient_count",
+      "page",
+      "has_next"
+    ]
+  },
+  {
+    "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: `api_unavailable`: USAspending.gov API is unreachable or returns an error. `api_timeout`: USAspending.gov did not respond before the request deadline elapsed. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "api_unavailable",
+            "api_timeout"
+          ],
+          "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: -[
-  "results",
-  "page_metadata",
-  "recipient_count",
-  "page",
-  "has_next"
-]

Changed15 schema fields changedJul 17, 2026

changedInput schema / properties / limit / description

Previous value: -"Maximum results to return (1–100)"New value: +"Maximum results per page (1–100)"

addedInput schema / properties / page

Added value: +{
+  "default": 1,
+  "description": "Page number (1-based) — request the next page to retrieve matches beyond the first",
+  "maximum": 9007199254740991,
+  "minimum": 1,
+  "type": "integer"
+}

removedOutput schema / properties / cap

Removed value: -{
-  "description": "The limit that was applied.",
-  "type": "number"
-}

addedOutput schema / properties / has_next

Added value: +{
+  "description": "Whether there are more pages of results",
+  "type": "boolean"
+}

changedOutput schema / properties / notice / description

Previous value: -"Recovery hint when results are empty — suggests how to broaden the search. Absent when results are present."New value: +"Recovery hint — how to continue to the next page when more results exist, or how to broaden the search when empty. Absent when the full match set fits on this page."

addedOutput schema / properties / page

Added value: +{
+  "description": "Current page number returned",
+  "type": "number"
+}

addedOutput schema / properties / page_metadata

Added value: +{
+  "additionalProperties": false,
+  "description": "Pagination metadata — page through with the page input to reach later matches",
+  "properties": {
+    "has_next": {
+      "description": "Whether there are more pages of results",
+      "type": "boolean"
+    },
+    "limit": {
+      "description": "Results per page",
+      "type": "number"
+    },
+    "page": {
+      "description": "Current page number",
+      "type": "number"
+    },
+    "total": {
+      "description": "Total matching recipients across all pages",
+      "type": "number"
+    }
+  },
+  "required": [
+    "page",
+    "has_next",
+    "limit"
+  ],
+  "type": "object"
+}

changedOutput schema / properties / recipient_count / description

Previous value: -"Number of matching recipients returned"New value: +"Number of matching recipients returned on this page"

removedOutput schema / properties / results / items / properties / location

Removed value: -{
-  "additionalProperties": false,
-  "description": "Recipient address location",
-  "properties": {
-    "city_name": {
-      "description": "City of recipient address",
-      "type": "string"
-    },
-    "country_code": {
-      "description": "Country code",
-      "type": "string"
-    },
-    "state_code": {
-      "description": "State code",
-      "type": "string"
-    }
-  },
-  "type": "object"
-}

removedOutput schema / properties / results / items / properties / state

Removed value: -{
-  "description": "State code of recipient address",
-  "type": "string"
-}

removedOutput schema / properties / shown

Removed value: -{
-  "description": "Number of recipients returned.",
-  "type": "number"
-}

removedOutput schema / properties / total

Removed value: -{
-  "description": "Number of results returned",
-  "type": "number"
-}

addedOutput schema / properties / totalCount

Added value: +{
+  "description": "Total matching recipients across all pages",
+  "type": "number"
+}

removedOutput schema / properties / truncated

Removed value: -{
-  "description": "True when results were capped at the limit.",
-  "type": "boolean"
-}

changedOutput schema / required

Previous value: -[
-  "results",
-  "total",
-  "recipient_count"
-]New value: +[
+  "results",
+  "page_metadata",
+  "recipient_count",
+  "page",
+  "has_next"
+]

Changed3 schema fields changedJun 12, 2026

addedOutput schema / properties / cap

Added value: +{
+  "description": "The limit that was applied.",
+  "type": "number"
+}

addedOutput schema / properties / shown

Added value: +{
+  "description": "Number of recipients returned.",
+  "type": "number"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when results were capped at the limit.",
+  "type": "boolean"
+}

Changed4 schema fields changedMay 30, 2026

removedOutput schema / properties / message

Removed value: -{
-  "description": "Recovery hint when results are empty — suggests how to broaden the search. Absent when results are present.",
-  "type": "string"
-}

addedOutput schema / properties / notice

Added value: +{
+  "description": "Recovery hint when results are empty — suggests how to broaden the search. Absent when results are present.",
+  "type": "string"
+}

addedOutput schema / properties / recipient_count

Added value: +{
+  "description": "Number of matching recipients returned",
+  "type": "number"
+}

changedOutput schema / required

Previous value: -[
-  "results",
-  "total"
-]New value: +[
+  "results",
+  "total",
+  "recipient_count"
+]

First observedMay 29, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations provide readOnlyHint and idempotentHint, so the safety profile is known. The description adds behavioral nuance beyond annotations: pagination mechanics (use page, page_metadata.total), return fields, and hierarchy level definitions (P, C, R). No contradiction with annotations.

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 compact and front-loaded. Each sentence serves a purpose: core search action, returned fields, pagination, and hierarchical level explanation. No wasted words; ideal length for an agent to quickly parse.

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?

Given the presence of an output schema (which covers return values), the description covers essential aspects: what to search, pagination behavior, and hierarchy codes. It also references the companion tool. Minor gaps like error handling or rate limits are not documented, but they are not required given the annotations and output schema. Complete for typical agent use.

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 all parameters. The description adds marginal semantics (e.g., 'partial matches are supported' is already in schema; pagination note aligns with page parameter but is more behavioral). No new parameter-level meaning is provided beyond the 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?

Clear verb+resource: 'Search for organizations or individuals receiving federal funds' by name, UEI, or DUNS. It distinguishes itself from siblings like usaspending_get_recipient by explicitly noting returned hash IDs feed into that tool. Purpose is specific and unambiguous.

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?

States clear context: search for recipients by identifier and that results are paginated. Mentions companion usaspending_get_recipient for full profiles, implying a follow-up path. However, it doesn't explicitly state when NOT to use this tool or compare with other search siblings (e.g., usaspending_search_awards), so not a full 5.

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

All usaspending-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.