openfec-mcp-server

Openfec Search Disbursements

openfec_search_disbursements

Read-onlyIdempotent

Search itemized committee spending (Schedule B) or get aggregate breakdowns by purpose or recipient. All modes require a committee_id. Use to answer "what is this committee spending money on?" or "who is receiving payments from this committee?"

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No	Query mode. "itemized" returns individual disbursement records (keyset pagination). "by_purpose" aggregates by purpose category. "by_recipient" aggregates by recipient name. "by_recipient_id" aggregates by recipient committee ID (committee-to-committee transfers).	itemized
`page`	No	Page number (1-indexed) for aggregate modes. Explicit page is rejected in itemized mode, which paginates with cursor. Defaults to 1 for aggregates.
`sort`	No	Sort field. A "-" prefix sorts descending: use "-disbursement_amount" for the biggest payments first, since the ascending form leads with the most negative rows (refunds and voided payments). Itemized only; OpenFEC sorts by "-disbursement_date" when omitted.
`cycle`	No	Two-year election cycle (e.g., 2024). Even years only. Itemized mode defaults to the current cycle when omitted — Schedule B spans all history, and an all-history scan of an active committee times out upstream. Pass an explicit cycle to search an earlier period.
`cursor`	No	Opaque pagination cursor from a previous response of this tool. Itemized mode only (keyset pagination). Valid only for an otherwise-identical call — changing any other argument, including sort, rejects the cursor; omit it to start over.
`max_date`	No	Latest disbursement date (YYYY-MM-DD). Itemized only.
`min_date`	No	Earliest disbursement date (YYYY-MM-DD). Itemized only.
`per_page`	No	Results per page. Itemized mode sends at most 30 upstream, keeping the response under a 100,000-byte budget; a page bounded below your request reports truncated and cap, and next_cursor continues it.
`max_amount`	No	Maximum amount in dollars. Itemized only.
`min_amount`	No	Minimum amount in dollars. Itemized only.
`committee_id`	Yes	Spending committee ID (e.g., C00703975). Get IDs from openfec_search_committees results. Required for all modes.
`recipient_city`	No	Recipient city. Itemized only.
`recipient_name`	No	Full-text payee name search. Itemized only.
`recipient_state`	No	Recipient state. Itemized only.
`recipient_committee_id`	No	Recipient committee ID (for committee-to-committee transfers). Itemized only.
`disbursement_description`	No	Full-text description search (e.g., "media buy", "consulting"). Itemized only.
`disbursement_purpose_category`	No	Purpose category code. Itemized only.

Output Schema

TableJSON Schema

Name	Required	Description
`cap`	No	The per_page this call applied in place of the one requested — the page-size ceiling for this tool and scope. Present only when truncated is true.
`mode`	No	Query mode as the server resolved it. Row shapes differ by mode — itemized rows are individual payments, aggregate rows are buckets with a total — so read this rather than inferring the shape from the fields present.
`count`	No	Total matching disbursements (itemized mode). Check count_is_approximate before quoting it as a figure.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Rows in this page. Present only when truncated is true.
`notice`	No	Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when disbursements did match, that the total is an estimate, or that the page was bounded below the per_page requested and how to continue.
`results`	No	Disbursement result set; itemized records or aggregate buckets depending on mode.
`committee`	No	The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object.
`truncated`	No	True when this page holds fewer rows than the per_page requested because a full page would exceed the 100,000-byte response budget, and more rows remain. Absent on a complete page, including a naturally short last page.
`pagination`	No	Page-based pagination info (aggregate modes only).
`totalCount`	No	Total matching disbursements or aggregate rows.
`next_cursor`	No	Pagination cursor for the next page of itemized results. Null when no more pages.
`search_criteria`	No	Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured.
`count_is_approximate`	No	True when OpenFEC reports count as an estimate rather than a tally, which it does on its highest-volume queries. Absent means the count is a tally.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 24, 2026

changedInput schema / properties / per_page / description

Previous value: -"Results per page."New value: +"Results per page. Itemized mode sends at most 30 upstream, keeping the response under a 100,000-byte budget; a page bounded below your request reports truncated and cap, and next_cursor continues it."

addedOutput schema / properties / cap

Added value: +{
+  "description": "The per_page this call applied in place of the one requested — the page-size ceiling for this tool and scope. Present only when truncated is true.",
+  "type": "number"
+}

changedOutput schema / properties / notice / description

Previous value: -"Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when disbursements did match, or that the total is an estimate."New value: +"Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when disbursements did match, that the total is an estimate, or that the page was bounded below the per_page requested and how to continue."

addedOutput schema / properties / shown

Added value: +{
+  "description": "Rows in this page. Present only when truncated is true.",
+  "type": "number"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when this page holds fewer rows than the per_page requested because a full page would exceed the 100,000-byte response budget, and more rows remain. Absent on a complete page, including a naturally short last page.",
+  "type": "boolean"
+}

Changed4 schema fields changedSep 22, 2026

changedOutput schema / properties / count / description

Previous value: -"Total result count (may be approximate for itemized)."New value: +"Total matching disbursements (itemized mode). Check count_is_approximate before quoting it as a figure."

addedOutput schema / properties / count_is_approximate

Added value: +{
+  "description": "True when OpenFEC reports count as an estimate rather than a tally, which it does on its highest-volume queries. Absent means the count is a tally.",
+  "type": "boolean"
+}

changedOutput schema / properties / notice / description

Previous value: -"Guidance when no disbursements matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when disbursements did match, or that the total is an estimate."

addedOutput schema / properties / pagination / properties / count_is_approximate

Added value: +{
+  "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.",
+  "type": "boolean"
+}

Changed3 schema fields changedSep 19, 2026

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it. `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply. Other values are possible when a failure originates below the handler."

removedOutput schema / properties / next_cursor / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / next_cursor / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed4 schema fields changedAug 31, 2026

removedInput schema / properties / page / default
```
Removed value: -1
```

changedInput schema / properties / page / description

Previous value: -"Page number (1-indexed) for the aggregate modes. Ignored in itemized mode, which paginates with cursor. Read pagination.pages in the response to see how many pages exist."New value: +"Page number (1-indexed) for aggregate modes. Explicit page is rejected in itemized mode, which paginates with cursor. Defaults to 1 for aggregates."

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "itemized_only_filters_in_aggregate_mode"
-]New value: +[
+  "itemized_only_filters_in_aggregate_mode",
+  "inputs_not_applicable_to_mode"
+]

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",
+      "mode",
+      "search_criteria",
+      "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: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "itemized_only_filters_in_aggregate_mode"
+          ],
+          "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",
-  "mode",
-  "search_criteria",
-  "totalCount"
-]

Changed4 schema fields changedJul 26, 2026

addedOutput schema / properties / committee

Added value: +{
+  "additionalProperties": {},
+  "description": "The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object.",
+  "properties": {},
+  "type": "object"
+}

addedOutput schema / properties / mode

Added value: +{
+  "description": "Query mode as the server resolved it. Row shapes differ by mode — itemized rows are individual payments, aggregate rows are buckets with a total — so read this rather than inferring the shape from the fields present.",
+  "enum": [
+    "itemized",
+    "by_purpose",
+    "by_recipient",
+    "by_recipient_id"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / search_criteria / description

Previous value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured."

changedOutput schema / required

Previous value: -[
-  "results",
-  "totalCount"
-]New value: +[
+  "results",
+  "mode",
+  "search_criteria",
+  "totalCount"
+]

Changed1 schema field changedJul 26, 2026

changedInput schema / properties / cycle / description

Previous value: -"Two-year election cycle (e.g., 2024). Even years only."New value: +"Two-year election cycle (e.g., 2024). Even years only. Itemized mode defaults to the current cycle when omitted — Schedule B spans all history, and an all-history scan of an active committee times out upstream. Pass an explicit cycle to search an earlier period."

Changed1 schema field changedJul 26, 2026

addedInput schema / properties / page

Added value: +{
+  "default": 1,
+  "description": "Page number (1-indexed) for the aggregate modes. Ignored in itemized mode, which paginates with cursor. Read pagination.pages in the response to see how many pages exist.",
+  "maximum": 9007199254740991,
+  "minimum": 1,
+  "type": "integer"
+}

Changed3 schema fields changedJul 26, 2026

changedInput schema / properties / cursor / description

Previous value: -"Opaque pagination cursor from a previous response. Itemized mode only (keyset pagination)."New value: +"Opaque pagination cursor from a previous response of this tool. Itemized mode only (keyset pagination). Valid only for an otherwise-identical call — changing any other argument, including sort, rejects the cursor; omit it to start over."

changedInput schema / properties / sort / description

Previous value: -"Sort field. Itemized only."New value: +"Sort field. A \"-\" prefix sorts descending: use \"-disbursement_amount\" for the biggest payments first, since the ascending form leads with the most negative rows (refunds and voided payments). Itemized only; OpenFEC sorts by \"-disbursement_date\" when omitted."

changedInput schema / properties / sort / enum

Previous value: -[
-  "disbursement_date",
-  "disbursement_amount"
-]New value: +[
+  "disbursement_date",
+  "-disbursement_date",
+  "disbursement_amount",
+  "-disbursement_amount"
+]

Changed1 schema field changedJun 8, 2026
- removedInput schema / properties / committee_id / pattern
```
Removed value: -"^C\\d+$"
```

Changed3 schema fields changedMay 30, 2026

addedOutput schema / properties / notice

Added value: +{
+  "description": "Guidance when no disbursements matched — echoes filters and suggests how to broaden.",
+  "type": "string"
+}

addedOutput schema / properties / totalCount

Added value: +{
+  "description": "Total matching disbursements or aggregate rows.",
+  "type": "number"
+}

changedOutput schema / required

Previous value: -[
-  "results"
-]New value: +[
+  "results",
+  "totalCount"
+]

Changed2 schema fields changedMay 27, 2026

changedInput schema / properties / committee_id / description

Previous value: -"Spending committee ID (e.g., C00703975). Required for all modes."New value: +"Spending committee ID (e.g., C00703975). Get IDs from openfec_search_committees results. Required for all modes."

addedInput schema / properties / committee_id / pattern
```
Added value: +"^C\\d+$"
```

Changed9 schema fields changedMay 8, 2026

changedInput schema / properties / per_page / description

Previous value: -"Results per page (max 100)."New value: +"Results per page."

addedInput schema / properties / per_page / maximum
```
Added value: +100
```
addedInput schema / properties / per_page / minimum
```
Added value: +1
```

changedInput schema / properties / per_page / type

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

changedOutput schema / properties / pagination / properties / count / description
```
Previous value: -"Total results."New value: +"Total result count."
```

changedOutput schema / properties / pagination / properties / page / description

Previous value: -"Current page number."New value: +"Current page number (1-indexed)."

changedOutput schema / properties / pagination / properties / pages / description
```
Previous value: -"Total pages."New value: +"Total number of pages."
```

changedOutput schema / properties / results / description

Previous value: -"Disbursement records (itemized) or aggregate rows."New value: +"Disbursement result set; itemized records or aggregate buckets depending on mode."

changedOutput schema / properties / results / items / description

Previous value: -"A disbursement record (itemized entry) or an aggregate row."New value: +"Itemized disbursement record (mode=itemized) or aggregate row (mode=by_purpose, by_recipient, by_recipient_id)."

Changed1 schema field changedApr 24, 2026
- addedOutput schema / properties / results / items / description
```
Added value: +"A disbursement record (itemized entry) or an aggregate row."
```
Changed4 schema fields changedApr 21, 2026
- addedOutput schema / properties / results / items / properties
```
Added value: +{}
```
- removedOutput schema / properties / results / items / propertyNames
```
Removed value: -{
-  "type": "string"
-}
```
- addedOutput schema / properties / search_criteria / properties
```
Added value: +{}
```
- removedOutput schema / properties / search_criteria / propertyNames
```
Removed value: -{
-  "type": "string"
-}
```
First observedApr 13, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered without description effort. The description adds only mode-level context and the committee_id requirement; it does not disclose response-shape differences, rate limits, or upstream timeouts, which are left to schema parameter notes.

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 sentences with no filler: the first establishes the primary function and alternatives, the second gives the universal requirement, and the third provides user-oriented guidance. It is front-loaded and appropriately sized for a complex tool.

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 17 parameters, a 100%-covered schema, read-only annotations, and an output schema, the description is nearly sufficient for tool selection and invocation. It lacks a brief mode-selection cue, such as 'start with itemized for detail, aggregate for summaries', and an explicit note that aggregate modes change the response shape, though those are recoverable from the schema.

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 baseline is 3; the tool description adds no parameter details beyond what the schema already states. Mentioning 'by purpose or recipient' maps to mode values, but that is not new semantic content.

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 a specific verb and resource: 'Search itemized committee spending (Schedule B)' plus aggregate breakdowns by purpose or recipient. It is clearly about outgoing committee payments, but it never explicitly contrasts with sibling tools like openfec_search_expenditures, so the differentiation is implied rather than stated.

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?

It states the required precondition ('All modes require a committee_id') and gives two concrete use cases ('what is this committee spending money on?' / 'who is receiving payments?'). It does not provide exclusions or point to alternatives such as openfec_get_committee_totals or search_expenditures, so it misses the top benchmark.

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

All openfec-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.