Integration
Connect Hume AI to ProxyCrawl
When something happens in Hume AI, your agent does the next thing in ProxyCrawl. Describe it 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 Hume AI and ProxyCrawl to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiAny 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 Hume AI can start in ProxyCrawl
When New Voice in Hume AI
then Scrape URL in ProxyCrawl
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 Hume AI and ProxyCrawl
Triggers and actions 4 triggers · 17 actions
- Chat ended (instant)
Fires when an EVI chat session ends (chat_ended webhook event).
- Chat started (instant)
Fires when a new EVI chat session begins (chat_started webhook event).
- New Voice
Triggers when a new voice is created.
- Tool call (instant)
Fires when EVI calls a registered tool during a conversation (tool_call webhook event).
- Add config
Create a new EVI configuration (voice assistant setup).
- Add prompt
Create a new system prompt for use in an EVI configuration.
- Add tool
Create a new tool definition that EVI can call during a conversation.
- Add voice
Save a new custom voice to the account from a TTS generation ID, for reuse in later speech requests.
- Convert voice
Convert the speech in an uploaded audio file into a different saved voice.
- Delete config
Delete an EVI configuration from the account.
- Delete voice
Delete a saved custom voice from the account.
- Generate Text to Speech
Convert text to speech using Hume AI's expressive text-to-speech technology.
- List configs
List the EVI configurations saved to the account.
- List prompts
List the prompts saved to the account.
- List tools
List the tool definitions saved to the account.
- List voices
List the custom voices saved to the account.
- Update config
Update an EVI configuration's name or description.
- Delete stored page
Delete one or more stored pages from Crawlbase Cloud Storage by rid. Returns a per-RID delete status.
- Get account usage
Retrieve monthly usage statistics for a Crawlbase product. Returns successes, failures, due amount, remaining credits, per-domain breakdown. Rate-limited to 1 request per 5 minutes.
- Get stored page
Retrieve a previously stored page from Crawlbase Cloud Storage by rid or by original url. Returns the stored body plus stored_at/original_status/cb_status; format=html|json controls the response envelope.
- Scrape URL
Fetch a target URL through Crawlbase's Crawling API, returning the rendered page body plus original_status/cb_status. Supports format=html|json|md, optional JS-token rendering params (page_wait, ajax_wait, scroll, css_click_selector), country routing, and store=true to also persist the page to Cloud Storage (returns rid). The general-purpose scrape/render/anti-bot-bypass endpoint.
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 Hume AI
Hume AI to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Hume AI to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Hume AI to MailchimpMailchimp marketing automation and email platform.
Hume AI to StripeStripe is a payment processing platform for online businesses.
Hume AI to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
Hume AI to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
More into ProxyCrawl
Bookingmood to ProxyCrawlBookingmood is commission free flexible booking software that helps rental businesses of all sizes to...
Rebrandly to ProxyCrawlRebrandly is the easiest way to create and share branded links (short URLs using your own domain name).
Smartsheet via API Token to ProxyCrawlSmartsheet is a work management and collaboration platform.
HubSpot to ProxyCrawlHubSpot is your all-in-one stop for all of your marketing software needs.
Questions
Hume AI and ProxyCrawl, answered
What can start an automation from Hume AI?
Any of Hume AI's 4 triggers in the catalog, including New Voice, Chat ended (instant), Chat started (instant) and Tool call (instant). Describe the moment in plain language and your agent picks the right one.
What can your agent do in ProxyCrawl when something happens in Hume AI?
Any of ProxyCrawl's 4 actions, including Get account usage, Get stored page, Scrape URL and Delete stored page. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from ProxyCrawl to Hume AI?
ProxyCrawl has no triggers in the catalog today, so automations start in Hume AI. If you need the other direction, ask: your agent reads ProxyCrawl's API documentation and adds it.
Do I have to build a connector for Hume AI or ProxyCrawl?
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.
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.