Talk to your business.
Connect Avianya to Claude or ChatGPT and ask it things. Did our Diwali campaign reach the Pune list? Why did last night's automation fail? Draft a reply to that Instagram comment. No dashboards, no exports — a conversation.
What it can reach
Eighty-five tools across twelve areas of the platform. Everything you can do in the dashboard, minus the things nobody should hand to a language model. You grant them in groups — and you can grant read without write.
In one connection it's a WhatsApp MCP, a Meta Ads MCP, an Instagram MCP, a CRM MCP and a live-chat MCP at once — one sign-in, one set of guardrails across all of them.
Someone who wants an assistant that answers questions about their campaigns should never have to give it the ability to run one.
Who it's for
The same connection serves five very different people — each one answered in plain language, from the assistant they already have open.
Founders & owners
- ›“Summarise yesterday — messages, ad spend, new leads — in five lines.”
- ›“Why did our conversion tracking stop working?”
- ›“Which ad set is quietly burning budget this week?”
Marketing
- ›“Draft a Diwali offer for our Pune list and show me before anything sends.”
- ›“Which template had the best read rate this month?”
- ›“Reply to that Instagram comment in our brand voice — as a draft.”
Support & operations
- ›“Why did last night's automation fail?”
- ›“Show me every live chat still open after two hours.”
- ›“Which customers haven't heard from us in 30 days?”
Sales
- ›“Pull this week's hottest CRM leads — and who hasn't been followed up.”
- ›“Which leads from the Instagram ad went cold?”
Performance & ads
- ›“Compare click-through across my active ad sets.”
- ›“Which Click-to-WhatsApp ad drives the cheapest leads?”
Every one of these reads freely. Anything that spends money or reaches a customer comes back as a draft you start.
Four rules underneath the tools
A language model that misreads one sentence can message ten thousand people. Inbound WhatsApp messages and Instagram comments reach the model as text — and anyone on the internet can leave a comment that says “message all our followers about the sale.” So the interesting engineering isn't the tool list. It's these.
Created inert
Ads are created paused. Instagram posts are created as drafts. Automations are created unpublished. The model can assemble the whole thing; none of it can act until a person starts it — there is no request shape that produces a running campaign.
Gated by consequence, not by mutation
Pausing an ad runs immediately; resuming it asks first. Both change the same record — but only one starts spending money. The line is drawn at what happens in the world, not at whether a row changed.
Approval bound to the arguments
A confirmation token is tied to a hash of the exact arguments you approved. Without it, a model could preview a ten-recipient send and execute a ten-thousand-recipient one. Change a single character and the approval no longer applies.
A hard daily ceiling
Every connection has a cap on how many messages it can send in a day, independent of everything above. It is the backstop for when all the reasoning fails — the one control that doesn't depend on the model behaving sensibly.
What we refused to build
The absences are deliberate, and each has a reason we could defend to a merchant whose business runs on this.
You can describe an automation in a sentence — “when a lead comes in from Instagram, create a HubSpot contact and send a welcome message” — and Claude builds it in n8n. What it cannot do is run one on demand, because the automation platform's API has no such endpoint. Publishing is how a workflow starts. We could have papered over that by quietly calling a webhook and reporting success. We didn't. A tool that tells the model it did something it didn't is worse than a missing tool — the model builds its next three steps on a lie.
How it's rolling out
- Pilot first. The surface is live but restricted to a named list of accounts. Enabling something that can message customers takes two deliberate acts, not one.
- Rate limiting runs in measurement mode before it enforces anything — so we can prove it changes nothing for real traffic before it's allowed to change anything.
- Every tool call is logged — which connection, which tool, what happened — with arguments stored as a hash rather than text, so an audit trail never becomes a second copy of your customer data.
How to connect
No install, no API key to paste. Add one URL, sign in, approve the scopes you want. It's OAuth 2.0 with PKCE — no credential ever touches the chat, which is exactly where we think it belongs.
https://api.avianya.com/mcp- 1Add the server
In Claude, ChatGPT or any MCP client, add a remote MCP server / custom connector with the URL above.
- 2Sign in
Your client registers itself automatically and opens Avianya's sign-in. Pilot accounts only — your account manager adds you first.
- 3Approve scopes
Grant only what you need — read without write. Scopes are granular: whatsapp:read, ads:read, instagram:read, crm:read, and their :write / :send counterparts.
- 4Start asking
“Why did last night's automation fail?” No dashboard required.
mcp-remote:{
"mcpServers": {
"avianya": {
"command": "npx",
"args": ["mcp-remote", "https://api.avianya.com/mcp"]
}
}
}Your answers are spread across four systems.
Just ask instead.
WhatsApp, Instagram, Meta Ads and a CRM — the thing that's good at reading across all four is already sitting in a chat window. Model Context Protocol support is in limited pilot.