Integration
Connect PocketSmith to OpenGraph.io
When something happens in PocketSmith, your agent does the next thing in OpenGraph.io. Describe it in plain language and the automation is built, tested on every branch and kept running.
Build it
What do you want PocketSmith and OpenGraph.io to do together?
Describe it and your agent reads both APIs, builds the automation, tests every branch and ships it. The list below is what exists today, not the limit.
Ask the assistant
You'll sign in before anything runs. What you typed comes with you.
Or work from Claude Code
Install the APIANT plugin for Claude Code and build, edit, test and read run history from your terminal. Every plan gets this, including free, and it spends no assistant credits.
Connect Claude CodeEverything your agent can do with PocketSmith and OpenGraph.io
Triggers and actions 1 trigger · 17 actions
Trigger
New transactionFires when a new transaction appears in the authorised user's PocketSmith accounts. Poll GET /users/{id}/transactions sorted by created/updated date, dedup on transaction id.
- Add category
Create a new category for the authorised user. POST /users/{id}/categories.
- Add transaction
Create a new transaction in a PocketSmith transaction account. POST /transaction_accounts/{id}/transactions.
- Delete category
Delete a category by id. DELETE /categories/{id}.
- Delete transaction
Delete a transaction by id. DELETE /transactions/{id}.
- Get account
Retrieve a single account by id. GET /accounts/{id}.
- Get category
Retrieve a single category by id. GET /categories/{id}.
- Get transaction
Retrieve a single transaction by id. GET /transactions/{id}.
- Update category
Update an existing category's title, colour or parent. PUT /categories/{id}.
- Update transaction
Update fields on an existing transaction (amount, payee, date, category, note, labels). PUT /transactions/{id}.
Action
Audit site Open Graph tagsReads a page's Open Graph, Twitter Card and HTML meta tags so you can see what a link to it will look like when shared.
- Capture Screenshot
Takes a screenshot of a web page and returns a link to the image.
- Convert page to markdown
Turns a web page into clean markdown text, ready to feed an AI step or store as an article.
- Extract page elements
Pulls named pieces out of a web page — headings, links, prices — using CSS selectors, plus the page's plain text.
- Generate embed card
Builds a ready-to-paste embed card for a link, returning the HTML that renders it.
- Query page content
Asks a question about a web page and returns an AI-written answer, optionally shaped into fields you specify.
- Retrieve Link Preview Data
Fetches the title, description, image and site name behind a link, so you can show a rich preview of it.
- Scrape HTML
Fetches the raw HTML of a web page, optionally running its JavaScript first.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.