Integration
Connect Fellow to Browserless
When New recording fires in Fellow, your agent runs Download a file in Browserless. 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 Fellow and Browserless 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 Fellow can start in Browserless
When New recording in Fellow
then Download a file in Browserless
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 Fellow and Browserless
Triggers and actions 1 trigger · 22 actions
- New recording
Triggers when a new meeting recording is created in Fellow.
- Add Talking Point
Adds a talking point to the end of a Fellow meeting note's agenda, leaving the existing agenda content in place.
- Archive action item
Archives a Fellow action item by marking it as won't do, and returns the updated action item.
- Complete Action Item
Marks a Fellow action item as complete, or reopens it as incomplete, and returns the updated action item.
- Delete note
Permanently deletes a Fellow meeting note. Requires an API key with super admin (privileged) access.
- Delete recording
Deletes a Fellow meeting recording by its ID. Requires an API key with super admin privileges.
- Get action item
Returns a single Fellow action item by its ID, including its text, status, due date, assignees and the note it belongs to.
- Get AI Note
Returns a Fellow meeting note by its ID, including its title, meeting details, attendees, linked recordings and the note content as markdown.
- Get recording
Returns a Fellow meeting recording, including its transcript, AI notes and the note it belongs to.
- List notes
Returns the meeting notes you can access in Fellow, optionally filtered by meeting, channel, title, attendees, or created/updated dates, with optional note content.
- List recordings
Returns the meeting recordings in your Fellow workspace, optionally filtered by calendar event, channel, title or created/updated dates, with transcripts and AI notes on request.
- Bypass bot detection
Load a URL through Browserless's /unblock endpoint to bypass CAPTCHAs and bot detection, returning rendered content, cookies, and/or a screenshot per requested data flags.
- Capture a Screenshot
Takes a screenshot from a URL.
- Crawl a website
Asynchronously crawl an entire site via Browserless's /crawl endpoint, scraping every page within the given depth/path filters and returning structured page data.
- Discover site URLs
Load a page in a real browser and return every link address found on it.
- Download a file
Run JavaScript code via Browserless's /download endpoint and retrieve a file that Chrome downloads during execution.
- Extract Data
Search for data within a website.
- Fetch a Site's HTML
Scrapes the full HTML contents of a website.
- Generate a PDF
Generate a PDF from a URL.
- Measure a Website's Performance
Get stats on a website's performance. (Google's Lighthouse tool)
- Run BQL Query
Executes a Browser Query Language (BQL) script for sequential automation steps.
- Run custom function
Execute server-side Puppeteer JavaScript code (with optional context object) via Browserless's /function endpoint and return the function's result.
- Search the web
Query Browserless's /search endpoint for web results, optionally scraping the result pages and returning structured JSON.
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 Fellow
Fellow to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Fellow to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Fellow to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Fellow to Google SheetsGoogle Sheets
Fellow to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Fellow to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Browserless
Lexware Office to BrowserlessLexware Office is a cloud app for german accounting.
Questions
Fellow and Browserless, answered
What can start an automation from Fellow?
Any of Fellow's 1 trigger in the catalog, including New recording. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Browserless when something happens in Fellow?
Any of Browserless's 12 actions, including Bypass bot detection, Capture a Screenshot, Crawl a website and Discover site URLs. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Browserless to Fellow?
Browserless has no triggers in the catalog today, so automations start in Fellow. If you need the other direction, ask: your agent reads Browserless's API documentation and adds it.
Do I have to build a connector for Fellow or Browserless?
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 Fellow and Browserless 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.