Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility. That is what the fonoster mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Fonoster is researching an innovative Programmable Telecommunications Stack that will allow businesses to connect telephony services with the Internet entirely through a cloud-based utility.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.
The server publishes 12 tools. What each one is for:
Answer — Accepts an incoming callHangup — Closes the callPlay — Takes a URL with a media file and streams the sound back to the calling partyPlayDtmf — Takes a DTMF sequence and plays it back to the calling partySay — Takes a text, synthesizes the text into audio, and streams back the resultGather — Waits for DTMF or speech events and returns back the resultSGather — Returns a stream for future DTMF and speech resultsStream — Creates a bidirectional stream to send and receive audio from a callerDial — Passes the call to an Agent or a Number at the PSTNRecord — It records the voice of the calling party and saves the audio on the Storage sub-systemMute — It tells the channel to stop sending media, effectively muting the channelUnmute — It tells the channel to allow media flowThis sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Fonoster's toolset — Answer, Hangup, Play and 9 more — is a fair guide to whether it matches your workflow. It is maintained by fonoster; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Answer | Accepts an incoming call |
| Hangup | Closes the call |
| Play | Takes a URL with a media file and streams the sound back to the calling party |
| PlayDtmf | Takes a DTMF sequence and plays it back to the calling party |
| Say | Takes a text, synthesizes the text into audio, and streams back the result |
| Gather | Waits for DTMF or speech events and returns back the result |
| SGather | Returns a stream for future DTMF and speech results |
| Stream | Creates a bidirectional stream to send and receive audio from a caller |
| Dial | Passes the call to an Agent or a Number at the PSTN |
| Record | It records the voice of the calling party and saves the audio on the Storage sub-system |
| Mute | It tells the channel to stop sending media, effectively muting the channel |
| Unmute | It tells the channel to allow media flow |
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.
Thousands of open models on tap — run image, video and audio generation through Replicate's hosted API.