Integration
Connect Hjarni to Agent Toolbelt
When New Note fires in Hjarni, your agent runs Compare stocks in Agent Toolbelt. 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 Hjarni and Agent Toolbelt 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 Hjarni can start in Agent Toolbelt
When New Note in Hjarni
then Compare stocks in Agent Toolbelt
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 Hjarni and Agent Toolbelt
Triggers and actions 1 trigger · 23 actions
- New Note
Triggers when a new note is created.
- Add File to Note
Attaches a file to an existing note from a URL.
- Add tag
Create a tag.
- Create Folder
Creates a new folder with a name, parent folder, description, and AI instructions.
- Create Note
Creates a new note with a title, body, tags, and folder.
- Delete folder
Delete a container.
- Delete note
Delete a note (moves to trash).
- Delete tag
Delete a tag.
- Get folder
Fetch one container by id.
- Get note
Fetch one note by id with body, tags, container, files.
- List notes
List notes, filter by scope/container_id/tag, paginated.
- List tags
List tags.
- Update folder
Update a container.
- Update note
Update note fields (title, body, tags, container, append_body etc, expected_lock_version).
- Update tag
Rename/update a tag.
- Compare stocks
/api/tools/compare-stocks. Head-to-head comparison of 2-3 tickers.
- Count tokens
/api/tools/token-counter {text, models}. Token counts across LLMs.
- Extract text data
/api/tools/text-extractor. Extracts structured data from raw text.
- Generate bull vs bear case
/api/tools/bear-vs-bull {ticker}. Steelmanned bull and bear cases.
- Generate stock thesis
/api/tools/stock-thesis {ticker}. Returns verdict, thesis, insider read, watch-for.
- Get valuation snapshot
/api/tools/valuation-snapshot {ticker}. Valuation verdict and buy zone.
- Normalize address
/api/tools/address-normalizer. Normalizes a US address to USPS format.
- Review portfolio
/api/tools/portfolio-review. Reviews held portfolio.
- Scan watchlist
/api/tools/watchlist-scan. Ranks a watchlist of 2-15 tickers.
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 Hjarni
Hjarni to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Hjarni to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Hjarni to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Hjarni to MailchimpMailchimp marketing automation and email platform.
Hjarni to StripeStripe is a payment processing platform for online businesses.
Hjarni to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
More into Agent Toolbelt
Ontraport to Agent ToolbeltOntraport is an all-in-one CRM, marketing automation, and e-commerce platform.
Google Sheets to Agent ToolbeltGoogle Sheets
Gmail to Agent ToolbeltGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Questions
Hjarni and Agent Toolbelt, answered
What can start an automation from Hjarni?
Any of Hjarni's 1 trigger in the catalog, including New Note. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Agent Toolbelt when something happens in Hjarni?
Any of Agent Toolbelt's 9 actions, including Compare stocks, Count tokens, Extract text data and Generate bull vs bear case. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Agent Toolbelt to Hjarni?
Agent Toolbelt has no triggers in the catalog today, so automations start in Hjarni. If you need the other direction, ask: your agent reads Agent Toolbelt's API documentation and adds it.
Do I have to build a connector for Hjarni or Agent Toolbelt?
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 Hjarni and Agent Toolbelt 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.