Integration
Connect Roam to JigsawStack
When New Recording fires in Roam, your agent runs Add file in JigsawStack. 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 Roam and JigsawStack 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 Roam can start in JigsawStack
When New Recording in Roam
then Add file in JigsawStack
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 Roam and JigsawStack
Triggers and actions 6 triggers · 32 actions
- Lobby Booked
Triggers when a lobby is booked.
- New Recording
Triggers when a new meeting recording is saved in your Roam.
- New Transcript
Triggers when a new transcript is saved in your Roam.
- On-Air: Event Created
Triggers when a new On-Air event is created.
- On-Air: Guest Added
Triggers when a guest is added to an On-Air event.
- On-Air: Guest RSVP Changed
Triggers when a guest changes their RSVP status on an On-Air event.
- Create Meeting Link
Creates a new Roam meeting link and returns its ID and shareable URL. Optionally set the host's email and the meeting's start and end times.
- Find User by Email
Looks up a member of your Roam organization by their email address and returns their profile, including user ID, name, photo and admin status.
- On-Air: Add Guest
Adds a guest to a Roam On-Air event by email, optionally setting their name, phone and RSVP status, and returns the created guest.
- On-Air: Find Event
Returns the On-Air events whose title contains the text you search for, taken from your most recent events. Returns an empty list when nothing matches.
- Send Channel Message
Posts a message to a Roam channel and returns the message's timestamp, which you can reuse to reply in the same thread.
- Send Direct Message
Sends a direct message to one person in Roam and returns the conversation ID plus the message's timestamp, which you can reuse to reply in the same thread.
- Add file
Uploads a file to JigsawStack file storage.
- Add prompt
Creates a reusable AI prompt template in the Prompt Engine.
- Classify text
Classifies input text/data against provided or inferred labels.
- Convert HTML
Converts HTML content to another format (e.g. PDF/image).
- Delete file
Deletes a stored file by key.
- Delete prompt
Deletes a Prompt Engine template by id.
- Generate embedding
Generates a vector embedding for input text/image.
- Generate image
Generates an image from a text prompt.
- Generate speech
Turns text into spoken audio and returns the generated audio file.
- Generate SQL
Converts a natural-language prompt into a SQL query.
- Get prompt
Retrieves a Prompt Engine template by id.
- List prompts
Lists Prompt Engine templates.
- NSFW
Quickly detect nudity, violence, hentai, porn and more NSFW content in images.
- Object Detection
Recognise objects within an image with great accuracy.
- Profanity
Check any text for profanity.
- Run prompt
Executes a saved Prompt Engine template with runtime inputs.
- Scrape webpage
Scrapes structured content/data from a given URL.
- Search web
Runs a web search query and returns ranked results.
- Sentiment Analysis
Perform sentiment analysis on a given text.
- Spam Check
- Speech to Text
Transcribe video and audio files with ease leveraging Whisper large V3 AI model.
- Spell Check
Check and correct spelling errors in a text.
- Summary
Generate smarter text summaries with AI
- Translate
Translate text from one language to another.
- Translate image
Translates text found within an image to a target language.
- vOCR
Recognise, describe and retrieve data within an image with great accuracy.
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 Roam
Roam to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Roam to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Roam to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
Roam to TrelloTrello is a visual collaboration tool that organizes projects into boards, lists, and cards.
Roam to JIRAAtlassian JIRA Cloud — issue tracking and project management.
Roam to ZoomZoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...
More into JigsawStack
Supernotes to JigsawStackCollaborative note-taking app for creating linked notecards with checklists, images, and tasks, with a REST...
SurveyMonkey to JigsawStackSurveyMonkey is the easiest way to create surveys and get answers.
HubSpot to JigsawStackHubSpot is your all-in-one stop for all of your marketing software needs.
Slack to JigsawStackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to JigsawStackGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Questions
Roam and JigsawStack, answered
What can start an automation from Roam?
Any of Roam's 6 triggers in the catalog, including New Recording, New Transcript, On-Air: Event Created and On-Air: Guest Added. Describe the moment in plain language and your agent picks the right one.
What can your agent do in JigsawStack when something happens in Roam?
Any of JigsawStack's 26 actions, including Add file, Add prompt, Classify text and Convert HTML. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from JigsawStack to Roam?
JigsawStack has no triggers in the catalog today, so automations start in Roam. If you need the other direction, ask: your agent reads JigsawStack's API documentation and adds it.
Do I have to build a connector for Roam or JigsawStack?
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 Roam and JigsawStack 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.