Givebutter

Search and fetch articles from Givebutter's help center (help.givebutter.com). Two actions: - action=search, params={query, limit?}: Returns up to 10 (max 25) articles matching the query with id, title, url, and a short excerpt. Use when the user asks a how-to question ("how do I refund a donation", "how does P2P work"). - action=get, params={id}: Returns a single article with the full body in plain text. Use after a search to read the complete answer rather than fetching the article URL externally. Help center articles are global — the same set is returned regardless of the calling account.

givebutter_help_center

Returns the field schema for an entity (contacts, transactions, transaction_plans, messages, auction_item_categories, pledges, campaign_members, campaign_teams, auctions, auction_bidders, campaigns, campaign_items, message_deliveries, events, tickets, funds, appeals, households, campaign_matches, tasks, workflows, widgets, giving_spaces). Call this BEFORE givebutter_query. The default call (entity only) returns a lightweight field index: per-field `{capabilities, nested_path?, resolves_references?}`. Operators, descriptions, value shapes, and metric allowlists are NOT in the index — they are pulled on demand. To get full detail for specific fields, call this tool again with `field_keys: ["<key>", ...]`. The expansion response includes type, description, filter operators, bucket types, metric functions, and pairs_with_* cross-references. Capabilities: - "filter": the field can be used in filters.filters[] - "bucket": the field can be used in aggregates.bucket - "aggregate": the field can be used in aggregates.metrics[] - "project": the field can be returned in row output (name it in the query `fields` array) Typical workflow: 1. Call with `entity` only to see what fields exist and their capabilities. 2. Decide which fields fit the user query. 3. Call again with `field_keys: [...]` to get full definitions. 4. Compose givebutter_query.

givebutter_load_entity_context

Runs a structured filter query against Givebutter entities (contacts, transactions, transaction_plans, messages, auction_item_categories, pledges, campaign_members, campaign_teams, auctions, auction_bidders, campaigns, campaign_items, message_deliveries, events, tickets, funds, appeals, households, campaign_matches, tasks, workflows, widgets, giving_spaces). Supports three modes: - Rows only (omit aggregates): returns matching rows. - Aggregates only (limit: 0 + aggregates block): returns aggregate totals and buckets, no rows. - Both (limit > 0 + aggregates block): returns matching rows AND aggregates in one call. Use this for "show me the list plus the total" questions. For a grouped aggregate (a bucket dimension), `aggregates.totals` is ALWAYS the grand total over the whole dataset, `aggregates.shown` is the subtotal of just the returned buckets, and `aggregates.categories` is the true number of groups. Buckets are capped (default top 30), so NEVER sum buckets or read `shown` as the total — read `aggregates.headline` to know which figure to report and how to label it. IMPORTANT: To request specific fields or use filter keys, FIRST call givebutter_load_entity_context to discover valid field names for the entity. Do not guess field names — unknown fields are rejected. Accepts filter clauses with key/op/value/combine fields. Campaign values can be passed by name — the server resolves them to IDs automatically. By default rows return a concise field set. Pass a `fields` array to choose exactly which fields come back; unknown field names are rejected with the valid set. Discover field names with givebutter_load_entity_context. Pass `sort` ([{field, dir}]) to order rows — use this plus limit for "top N" questions (e.g. sort by total_contributions desc, limit 10). Rows are paginated. The response carries `count` (this page), `total` (all matches), and `flags.truncated`. When truncated is true, more rows exist — request the next page with `offset` = previous offset + limit. All monetary amounts — filter values and result metrics — are in US dollars (e.g., 100 = $100). Never send or expect cents. When the aggregates block is present, metrics.fn must be one of: count|sum|avg|min|max|distinct. bucket.type must be time_bucket or terms. All bucket and metric fields must share the same nested path. A top-level intent field (a sibling of entity and aggregates, NOT nested inside the aggregates block) is required when aggregates is present. For counting rows, use {"fn":"count","field":"*","alias":"total"}. For counting distinct values of a specific field, use {"fn":"distinct","field":"<field_name>","alias":"distinct_count"}.

givebutter_query

Returns a snapshot of the Givebutter account in scope: id, name, timezone, and created_at. Call this once at the start of a session so subsequent answers can name the account explicitly. Use `id` to build dashboard URLs (dashboard.givebutter.com/accounts/{id}/...). Includes the account NCF (Nonprofit Context File): mission, voice, branding, and other grounding context when available, or null when the account has no context yet.

givebutter_who_am_i

Returns embed snippets for all platforms for an existing widget display_id. Snippets returned: - custom_element: the HTML custom element tag - wordpress_shortcode: WordPress [givebutter-widget id="..."] shortcode - wix_id: the raw display_id for Wix embed - script_tag: the JS library <script> tag with account aid and optional platform param This tool formats an existing display_id. To create a new widget, use givebutter_create_widget.

givebutter_widget_helper