Integration
Connect DocuPipe to Harvard Art Museums
When Document Processed fires in DocuPipe, your agent runs Find exhibitions by criteria in Harvard Art Museums. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want DocuPipe and Harvard Art Museums to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What DocuPipe can start in Harvard Art Museums
When Document Processed in DocuPipe
then Find exhibitions by criteria in Harvard Art Museums
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with DocuPipe and Harvard Art Museums
Triggers and actions 1 trigger · 25 actions
- Document Processed
Triggers when a document finishes parsing and OCR is complete.
- Add schema
Creates a new extraction schema in DocuPipe from a JSON schema you supply, and returns its schema ID.
- Analyze document
Asks DocuPipe a list of plain-language questions about one document and starts the analysis, returning the analysis ID to fetch the answers with.
- Classify Document
Sends one or more documents to DocuPipe to be sorted into your classes, and returns the job that is doing the work.
- Delete document
Removes a document from your DocuPipe account.
- Delete schema
Removes an extraction schema from your DocuPipe account.
- Extract Data From Document
Pulls structured data out of a document using one of your schemas, and returns the extraction to fetch the results with.
- Find documents by criteria
Finds documents in your DocuPipe account whose file name or document ID matches what you search for.
- Get Document
Returns one document from your DocuPipe account, with its file details, processing status, parsed text and your own metadata.
- Get Extraction Result
Returns the data DocuPipe pulled out of a document, shaped by the schema that was used, along with per-field confidence details.
- Get schema
Returns one extraction schema from your DocuPipe account, including the JSON schema it applies and its guidelines.
- List documents
Returns the documents in your DocuPipe account, optionally narrowed to one dataset or a date range.
- List extractions
Returns the data extractions in your DocuPipe account, optionally narrowed to one schema, one document, or a specific set of extractions.
- List schemas
Returns the extraction schemas in your DocuPipe account.
- Upload and Extract Data
Sends a file to DocuPipe and immediately starts pulling structured data out of it, returning both the new document and the extraction.
- Upload Document
Sends a file to DocuPipe to be read and turned into a document you can extract data from.
- Find exhibitions by criteria
Searches the Harvard Art Museums exhibitions by keyword, venue, person, status or date and returns the matching exhibitions.
- Find objects by criteria
Searches the Harvard Art Museums collection and returns the objects that match the criteria you give, such as keyword, title, artist, classification or year made.
- Find people by criteria
Searches the Harvard Art Museums people (artists, sitters, donors, authors and more) by criteria and returns the matching person records.
- Find publications by criteria
Searches the Harvard Art Museums publications that have been written about or illustrate artworks in the collection, by keyword, person, group, year or other criteria.
- Get exhibition
Returns the full record for one Harvard Art Museums exhibition, including its venues, images, publications and videos.
- Get object
Returns the full record of one object in the Harvard Art Museums collection, including its people, images, exhibitions and publications.
- Get person
Returns the full record for one person associated with the Harvard Art Museums collections, such as an artist, sitter, donor or author.
- List classifications
Returns the classifications Harvard Art Museums curators use to categorize items in the collections, such as Prints or Sculpture, with each one's object count.
- List cultures
Returns the cultures used to describe items in the Harvard Art Museums collections, optionally filtered by a search.
- List galleries
Returns the galleries in the Harvard Art Museums building, optionally filtered by floor or a search query.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from DocuPipe
DocuPipe to PubloraPublish and schedule posts to ten social networks from one endpoint
DocuPipe to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
DocuPipe to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
DocuPipe to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
DocuPipe to Google SheetsGoogle Sheets
DocuPipe to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
More into Harvard Art Museums
Google Calendar to Harvard Art MuseumsGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
DocuPipe and Harvard Art Museums, answered
What can start an automation from DocuPipe?
Any of DocuPipe's 1 trigger in the catalog, including Document Processed. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Harvard Art Museums when something happens in DocuPipe?
Any of Harvard Art Museums's 10 actions, including Find exhibitions by criteria, Find objects by criteria, Find people by criteria and Find publications by criteria. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Harvard Art Museums to DocuPipe?
Harvard Art Museums has no triggers in the catalog today, so automations start in DocuPipe. If you need the other direction, ask: your agent reads Harvard Art Museums's API documentation and adds it.
Do I have to build a connector for DocuPipe or Harvard Art Museums?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use DocuPipe and Harvard Art Museums without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.