Connect our MCP server to Claude, ChatGPT, your CRM — or agent platforms like OpenClaw and Hermes — and just say what you need. A plain human command becomes a real phone conversation, and the result comes back to the chat as structured data. Now it works the other way too: give your agent a number people — including you — can call.
One config block · 13 MCP tools · outbound live, inbound in early access · sandbox to try without real calls
A command in the chat → a real call → the result back. This is the whole product.
This is what using it feels like — inside Claude, ChatGPT or your own agent.
Give your agent a number people can call — including you. The same engine answers, understands, acts, and hands back a result.
Call in to brief your agent, assign a task or check status from any phone, hands-free — or let your customers reach an AI receptionist that looks things up, files to your CRM, and transfers to a human when it should. The same tools your agent uses outbound answer the inbound call.
Same task-in, result-out model — extended to WhatsApp and Telegram voice, so one agent voice channel spans the networks your customers actually use. In design with early-access pilots; tell us which channels you need in the form.
Claude / ChatGPT / OpenClaw / your CRM bot passes the human command as-is — “remind everyone about tomorrow's webinar and ask who's coming”. No prompt engineering on your side.
The task is compiled into a protected system prompt: the bot introduces itself, discloses recording, stays on task, resists prompt injection from the person on the line, and knows when to hang up.
Transcript, outcome and your structured fields (evidence-grounded — nothing invented) come back to the agent chat and to your CRM via signed webhooks. Opt-outs land in the DNC list automatically.
Standard MCP over streamable HTTP — the same server works in every client.
// Claude Desktop / Claude Code — mcp config { "mcpServers": { "voxtelai": { "type": "http", "url": "https://<your-endpoint>/mcp", "headers": { "Authorization": "Bearer <your-token>" } } } } # then, in chat: "Call +49 30 901820 and ask if they're open on Saturday" "Ring all contacts in leads.csv, offer the July discount, log who's interested"
start_call · get_call · list_calls · cancel_call · create_campaign · start/pause/resume/cancel/retry_campaign · get_campaign · list_campaigns · manage_dnc. Your agent composes them on its own.
Simulated mode + magic numbers run the whole pipeline — your agent “makes calls”, gets realistic results, and you see exactly what production will look like. Zero spend.
If it speaks MCP or HTTP, it can make calls.
Desktop, Code and API — add the server, and phone calls become a native tool in every conversation.
Connect through apps/connectors with the same streamable-HTTP endpoint — your GPT gains a real phone.
Personal agent platforms get calling superpowers: “book me a dentist appointment” now actually happens.
amoCRM, HubSpot, GoHighLevel, self-built — REST API + signed webhooks with your lead ids round-tripping through every event.
HTTP nodes today, native nodes on the roadmap — trigger calls from any workflow.
LangChain, CrewAI, AutoGen — wrap the MCP tools and give your fleet a voice channel.
Every call discloses it's automated and that the line is recorded. Verbal opt-outs go straight to your do-not-call list. Vague or risky commands fail closed — the compiler refuses rather than improvises. Pilots go through use-case review: your agent gets a phone, not a loophole.
Same engine, same bill as our API product: AI + telephony together, on our own carrier network.
AI conversation + telephony
Concierge pilot
Anything that speaks MCP over streamable HTTP with headers — Claude Desktop/Code, ChatGPT connectors, OpenClaw, custom agents on the official SDKs. One endpoint, Bearer auth, no local install.
The compiler fails closed: if a task can't be turned into a safe, unambiguous call script, the tool returns an error explaining what's missing instead of calling and improvising. Your agent can refine and retry.
The call script is compiled with injection resistance — instructions from the callee are treated as conversation, not commands. The bot stays on task, and everything is in the transcript you get back.
We're a carrier: termination almost anywhere, DIDs in 100+ countries. Conversations run on Gemini realtime voice — strong in English, Russian and most major languages. We validate your destinations in the pilot.
Yes — see the Inbound section. Outbound is in production today; inbound (a number your agent answers, as a control channel for you or an AI receptionist for your customers) is in early access. Omnichannel voice over WhatsApp and Telegram is in design. Tell us in the form which you need and we'll loop you into the pilot.
Tell us what your agent should be able to do — you get an MCP endpoint, a sandbox tenant and an engineer on a direct line.