Integration
Connect Corymbus to Geekflare
When New Activity fires in Corymbus, your agent runs Capture Screenshot in Geekflare. 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 Corymbus and Geekflare 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 Corymbus can start in Geekflare
When New Activity in Corymbus
then Capture Screenshot in Geekflare
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 Corymbus and Geekflare
Triggers and actions 2 triggers · 27 actions
- New Activity
Triggers when a new activity is created in Corymbus, optionally limited to activities linked to a given account, contact or opportunity, or owned by a given user.
- New Contact
Triggers when a new contact is created in Corymbus, optionally limited to contacts matching a name, account, activity, opportunity, group or owner.
- Add activity
Creates a new activity (task, call, meeting, note or email) in Corymbus and returns the created activity.
- Connect entities
Connects two Corymbus records together, for example an opportunity to an activity or a contact to an account.
- Create Account
Creates a new account (company) in Corymbus CRM and returns the created account.
- Create Contact
Creates a new contact (person) in Corymbus, optionally linked to an account, and returns the created contact.
- Create Opportunity
Creates a new opportunity (deal) in Corymbus, optionally linked to an account, with an amount, status and expected close date.
- Find Account
Finds accounts whose name contains the given text, optionally limited to an owner or a connected activity, and returns the matches.
- Find activities
Returns the activities whose name contains the text you give, optionally narrowed to an account, contact, opportunity, owner or late activities.
- Find contacts
Returns the Corymbus contacts whose first or last name contains the text you give, optionally narrowed by account, activity, opportunity, group or owner.
- Find opportunities
Returns the opportunities whose name contains the text you specify, optionally narrowed by account, contact, activity, owner or expected close period.
- Capture Screenshot
Take full-page screenshots of any website. Automatically handles JS rendering, cookie banners, ad-blocking, and mobile emulation.
- Check broken links
Scan a webpage for broken links and report which URLs return errors.
- Check DNSSEC status
Check whether DNSSEC is properly configured and validating for a domain, confirming protection against DNS spoofing and cache poisoning.
- Check mixed content
Scan an HTTPS page for insecure HTTP resources (images, scripts, stylesheets) that trigger browser security warnings.
- Check site status
Check whether a website is reachable and returns a successful HTTP response; useful for uptime monitoring.
- Check URL redirects
Trace the full redirect chain of a URL, including every intermediate hop, status code, and final destination.
- Extract Data From Website
Extracts data from public web pages into clean Markdown, HTML, or JSON.
- Generate PDF
Convert a URL into a downloadable PDF document, with control over page orientation, margins, and scale.
- Get brand info
Retrieve structured brand information for a domain (name, colors, fonts, logos, social profiles, page metadata).
- Lookup DNS Records
Lookup any domain and retrieve A, AAAA, MX, TXT, and other records.
- Measure load time
Measure how long a webpage takes to fully load from a real browser, optionally testing from up to 3 additional target countries via proxy.
- Ping host
Send ICMP ping requests to a URL or IP and return latency, packet loss, and round-trip time statistics.
- Run Lighthouse audit
Run a Google Lighthouse audit for performance, SEO, accessibility, and best practices, with support for advanced flags.
- Run MTR diagnostic
Run a My Traceroute (MTR) diagnostic between Geekflare and a target host, combining traceroute and ping to show packet loss and latency at each hop.
- Scan ports
Scan a domain or IP for open TCP ports (top N common ports or a custom range), with optional service/version detection.
- Scan TLS configuration
Inspect a domain's TLS/SSL configuration (supported protocol versions, certificate details) to catch expiring certificates and outdated configs.
- Scrape page metadata
Extract a page's meta tags, Open Graph, and Twitter Card data (title, description, canonical URL, images) without scraping the full page body.
- Search Web
Searches the web and optionally extracts page content to provide real-time context for AI agents and LLMs.
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 Corymbus
Corymbus to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Corymbus to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Corymbus to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Corymbus to Google SheetsGoogle Sheets
Corymbus to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Corymbus to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Geekflare
Questions
Corymbus and Geekflare, answered
What can start an automation from Corymbus?
Any of Corymbus's 2 triggers in the catalog, including New Activity and New Contact. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Geekflare when something happens in Corymbus?
Any of Geekflare's 18 actions, including Capture Screenshot, Check broken links, Check DNSSEC status and Check mixed content. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Geekflare to Corymbus?
Geekflare has no triggers in the catalog today, so automations start in Corymbus. If you need the other direction, ask: your agent reads Geekflare's API documentation and adds it.
Do I have to build a connector for Corymbus or Geekflare?
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 Corymbus and Geekflare 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.