Skip to main content
Glama

KeyVex

get_fec_disbursements

Read-only

Returns FEC Schedule B disbursements — itemized records of money flowing OUT of a federal committee to organisations: vendor payments, media / ad buys, consulting firms, payroll services, and committee-to-committee transfers. The OUT-flow counterpart to get_fec_contributions (Schedule A, money IN). ORGANISATIONS ONLY: per-record rows are served only when FEC codes the payee as a committee or organisation (COM, CCM, PAC, PTY, ORG). Rows naming a natural person — individual payees (IND), candidates (CAN), unclassified payees, and people a filer coded as an organisation — are withheld per record under the FEC sale-or-use rule (11 CFR 104.15). Refunds of contributions to individuals are withheld with them. Source: api.open.fec.gov/v1/schedules/schedule_b/ — the official FEC public-disclosure API. Live queries cover every itemized row; the cached fallback subset carries a $1,000+ ingestion floor (filters small-vendor / payroll noise). Publication-lag caveat: disbursements only surface when the spending committee FILES its report — monthly filers lag ~20 days, quarterly filers up to ~50 days after the spend. Short since/until windows on recent dates will miss rows whose reports haven't been filed yet. Killer query patterns: - What does candidate X's campaign spend money on? Pass spender_committee_id (their principal campaign committee from get_fec_candidate_profile). Sort by amount DESC for big spends. - Which campaigns pay consulting firm Y? Pass recipient_name='Y'. - Ad-spending patterns: disbursement_purpose_category='ADVERTISING' + cycle=2026 + sort_by=disbursement_amount DESC. - Money moving between committees: disbursement_purpose_category= 'TRANSFERS' — recipient_committee_id on each row names the receiving committee. Filter combinations note: server-side indexes support one equality filter (spender_committee_id / candidate_id / disbursement_purpose_category / recipient_state) combined with date or amount sort + cycle. Other filters (recipient_name substring, entity_type, exclude_memos) are applied client-side after a wider pre-fetch. Purpose categories (disbursement_purpose_category): ADVERTISING, CONSULTING, CONTRIBUTIONS, FUNDRAISING, PAYROLL (labeled 'SALARIES' on some rows), TRANSFERS, TRAVEL, ADMINISTRATIVE, MATERIALS, EVENTS, LOANS, REFUNDS, POLLING, OTHER. Memo rows: FEC tags certain aggregate / subtotal rows with memoed_subtotal=true. These DUPLICATE dollars already counted on other rows — KeyVex DEFAULTS to exclude_memos=true to show real money movement; pass exclude_memos=false to include the raw memo rows (e.g. for matching FEC's own row counts).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cycleNoElection cycle year (2-year transaction period). Common values: 2026, 2024, 2022.
limitNoMaximum disbursements to return. Default 50, max 500.
sinceNoInclusive lower bound on disbursement_date (YYYY-MM-DD).
untilNoInclusive upper bound on disbursement_date (YYYY-MM-DD).
sub_idNoFEC sub_id (globally unique row ID). Direct doc lookup, fastest.
sort_byNoSort key. Default: disbursement_date.
max_amountNoInclusive upper bound on disbursement_amount.
min_amountNoInclusive lower bound on disbursement_amount in dollars. KeyVex's cached subset holds $1,000+ rows; live queries cover every itemized row.
sort_orderNoDefault: desc (most recent / largest first).
entity_typeNoRecipient entity type code — ORGANISATION types only: COM (committee), CCM (candidate committee), PAC, PTY (party), ORG (organization — most vendors). IND (individual), CAN (candidate — a natural person) and UNK (unclassified) are not accepted: those rows are withheld under 11 CFR 104.15.
candidate_idNoFEC candidate ID tied to the disbursement (e.g., 'S6PA00091'). NOTE: only populated on candidate-linked rows; most vendor payments carry no candidate_id — prefer spender_committee_id for a campaign's full spending picture.
exclude_memosNoWhen true (DEFAULT), filters out rows flagged memoed_subtotal=true — FEC's aggregate / subtotal duplicates that double-count the same dollars across multiple rows. Pass exclude_memos=false to include them (useful for matching FEC's own raw row counts).
recipient_nameNoCase-insensitive substring against the payee's filed name (vendor, consulting firm or committee — natural persons are withheld, so a person's name returns nothing). Substring filter (client-side on the cached path).
recipient_stateNo2-letter US state code of the recipient (e.g., 'CA', 'TX').
spender_committee_idNoFEC committee ID doing the spending (e.g., 'C00580100'). Use get_fec_candidate_profile to find the principal committee for a candidate.
disbursement_purpose_categoryNoFEC's normalized purpose bucket (e.g., 'ADVERTISING', 'CONSULTING', 'CONTRIBUTIONS', 'FUNDRAISING', 'TRANSFERS', 'TRAVEL', 'PAYROLL', 'OTHER').

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/non-destructive, yet the description adds substantial behavior the agent could not infer: per-record withholding of individual payees under 11 CFR 104.15, the $1,000+ cached-subset floor, publication lag by filer type (~20 vs ~50 days), and the memo double-counting default. These are exactly the traits that change how an agent should interpret empty results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded and clearly sectioned, but roughly 400 words with noticeable repetition — the memo/exclude_memos behavior and the organisation-only rule are each explained in both the description and the schema, and the org-code list is restated. Length is partly justified by 16 parameters and a complex domain, but it is not tight.

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?

For a 16-parameter, no-output-schema, high-complexity tool, the description covers the gaps an agent needs: what is withheld and why, ingestion floor, filing lag, filter execution model, and default behaviors. Nothing essential to correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3), but the description adds meaning beyond the schema: the full purpose-category vocabulary, the server-side vs client-side filter split, and the guidance that candidate_id is sparse so spender_committee_id is preferred for a campaign's full picture. That materially changes how parameters are chosen.

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?

Opens with a specific verb+resource ('Returns FEC Schedule B disbursements') and immediately scopes the content (vendor payments, ad buys, transfers). It explicitly positions itself as 'the OUT-flow counterpart to get_fec_contributions (Schedule A, money IN)', which lets an agent separate the two siblings without reading either schema.

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?

Provides four named 'killer query patterns' with concrete parameter combinations for distinct intents (candidate spending, vendor lookup, ad-spend trends, committee transfers), plus a filter-combination note explaining which filters are server-side indexed vs client-side. Also states the one-equality-filter constraint, which is real routing guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources