Official scripts
Explore our curated collection of scripts
Create Pipedrive lead
Create a new lead in Pipedrive's Leads Inbox via the "+ Lead" quick-add form, setting the contact person's name as a new contact. Returns the new lead's id and detail-page URL.
List Pipedrive deals
List deals from Pipedrive's Deals list view, reading whatever columns the current view shows (title, value, organization, contact person, expected close date, next activity date, owner). Returns each deal's id and its visible column values.
Vercel — list invoices
List a Vercel team's billing invoices, newest first: billing period, status, total due, invoiced date, invoice id, a direct PDF download link, and a link to the invoice's detail page. Optionally pass a team URL slug; defaults to the account's own scope.
Subscribe to Substack publication
Subscribe the logged-in account to a Substack publication's free tier.
List a Google Drive folder
List the files and sub-folders directly inside a Google Drive folder, without recursing or downloading anything. Returns each item's id, name, type, size, last-modified date, owner and link. Omit folderId to list My Drive's root.
Download Stripe invoice/receipt PDF
Download a Stripe-hosted invoice or payment receipt PDF from its hosted_invoice_url. Returns the PDF bytes as base64 (decode + write it yourself) plus the real filename. Vendor-agnostic and login-free: the hosted_invoice_url is a public tokenized link, so it works for any Stripe-billed service (Claude, ChatGPT, Notion, Slack, Lovable, ...). An expired or dead URL fails cleanly.
Search Google Drive
Search Google Drive by free text, or filter by name, file type, owner and modified-date range. Returns each match's file id, name, link and the folder it sits in. Drive's search results carry no sizes, types or dates, so filter by type rather than expecting those fields back, and use the folder listing script when you need full metadata.
Maps: Search Businesses
Search for businesses on Google Maps (anonymous, no login): name, category, address, phone, website, rating, reviews, GPS, place_id. Paginates via scrolling, controlled by the count argument.
List connector Claude directory
Every connector in Claude's Directory (Settings → Connectors → Add → Browse connectors) — the whole catalogue the page loads, not one page. Each entry carries id, slug, name, one-liner, verified tier (anthropic/partner/community), categories, author, its claude.ai/directory link and the MCP endpoint URL. The Directory's Plugins tab (local extensions) is a different affordance and is not returned.
List Surfshark invoices/receipts
List and download Surfshark payment receipts from your account's subscription payments page. Returns total and invoices (purchase, date, amount, status, filename, PDF content); each successful payment's receipt PDF is included as base64, while cancelled or failed payments have none and are skipped. Works regardless of the account's display language.
Ashby: get company jobs
Fetch a company's live job postings from its public Ashby job board by hosted-jobs-page slug (jobs.ashbyhq.com/<slug>). Anonymous, no auth. Returns id, title, team name, location, workplaceType, employmentType and compensationTierSummary. Throws if the slug doesn't resolve to any organization.
Like Substack post
Like a Substack post as the logged-in account.
List OpenAI API invoices
List invoices on the OpenAI API platform billing account (platform.openai.com, api usage/credits — NOT the ChatGPT subscription). Returns id, number, total (cents), currency, status, created_ts, hosted_invoice_url, pdf_url. Covers the past 12 months, as the dashboard does.
Search Wise transactions
Search a Wise profile's transactions by merchant/name (server-side), optionally narrowed to a date range. Returns id, title, amount, date, status and whether a receipt is attached.
Download a Miro invoice PDF
Download one Miro company billing invoice PDF, given the pdfUrl that miro.com/list_invoices returns. Saves the file to the device and returns its real filename plus the path it was saved to. Unlike the other download_invoice scripts it hands back a file on disk rather than the bytes inline, because Miro only releases these PDFs through a real browser download — so read the file from the returned path. Requires access to Miro company billing.
Search YC startup directory
Search the YC startup directory (ycombinator.com/companies) by free-text query plus filters such as batch, industry, tag, region, status, and top/hiring/nonprofit; each multi-value filter is OR'd within itself. Zero-based pagination.
Browse Yelp businesses by category
Browse Yelp businesses in a specific category (e.g. 'pizza', 'plumbing') and location, using Yelp's category filter rather than free-text search. Returns matching businesses with name, url, rating, review count, price range, and categories.
Calendly: download invoices
Log into Calendly via Google SSO, list billing invoices, and download each invoice's PDF into the browser's download directory. Returns per invoice date, title, amount, currency, status, invoiceId, chargeId, filename and path (path is null when no PDF was available for that charge). Runs only on the browser extension, since it needs a native Google SSO session. Org admin only.
List supplier invoices
Lists Pennylane supplier invoices from one tab (All / Inbox / To pay / Paid / To approve). Returns each invoice's id, provider (best-effort, parsed from the site-generated label), invoice number, dates, amount/currency, payment status and paid flag. Requires companyId (the number in the app URL at /companies/<id>/supplier_invoices); defaults to the Inbox tab, the invoices needing reconciliation.
Download Cloudflare invoice/receipt
Download a single Cloudflare billing-history entry's PDF by accountId + invoiceId (from cloudflare.com/list_invoices). Returns the PDF bytes as base64 plus a filename.
Download an Atlassian invoice PDF
Download one Atlassian (admin.atlassian.com) billing invoice, given the downloadUrl — or the id plus transaction_account — that admin.atlassian.com/list_invoices returns. Returns the real filename plus the PDF bytes as base64 (decode and write it yourself). The bytes come back with the run, so it does not depend on the browser's own download folder, and it still works when Atlassian serves the PDF from a signed storage location. Only an org billing admin can download invoices.
Search Wizbii jobs
Searches job listings on jobs.wizbii.com by filtering by business domain (slug required, e.g. developpement-informatique, marketing, ventes — full list at wizbii.com/directory/lp/domaine) and optionally by city (slug, e.g. paris, lyon — list at wizbii.com/directory/lp/ville). No free-text keyword search: the site only exposes this category×city filter. Returns the site's own richer listing data for each result. An invalid domain or city throws explicitly rather than returning an empty page. 1-based pagination, matching the site's own URL.
Download a Slack invoice PDF
Download one Slack billing statement, given the pdfUrl or billId that slack.com/list_invoices returns. Returns the real filename plus the file bytes inline as base64, so decode and write it yourself — nothing is left on disk. Requires being a workspace billing admin.
List HubSpot invoices
List the billing invoices on a HubSpot account, taken from Account & Billing → Transactions: each invoice's number, date, amount, status, and a link to its PDF. The PDF link is tied to the signed-in session, so it only opens while that session is still active. Sign in to HubSpot in the browser this runs against before using it — signed out, the script says so rather than returning an empty list. Pass portalId to target a specific portal when the account has more than one.
Upload a file to Google Drive
Upload a file into a Google Drive folder, or into My Drive when no folder is given. Pass the bytes inline as base64 for small files, or point fileUrl at the file served over http://127.0.0.1:<port>/ on the machine running the browser for larger ones. Before reporting success it waits for a row in the destination that was absent beforehand AND carries this call's own filename, so it cannot credit itself with a file another upload created; it returns that file's Drive id. A filename already present in the destination is refused up front, because a dropped file does NOT replace or get declined — Drive happily stores a second, separate file under the same name. For the same reason a lost upload is reported as a failure rather than retried: a re-drop would duplicate an upload that merely landed slowly.