mcpField
S
saperly

saperly

Local
github.com/idanbier999Communication

About saperly

Phone carrier for AI agents. Provision numbers, make calls, send SMS, TCPA compliance built-in

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"idanbier999-saperly": {
"command": "npx",
"args": [
"-y",
"@saperly/mcp"
],
"env": {
"SAPERLY_API_KEY": "<SAPERLY_API_KEY>",
"SAPERLY_BASE_URL": "<SAPERLY_BASE_URL>"
}
}
}
}
Run commandnpx -y @saperly/mcp
Environment variables to set
SAPERLY_API_KEYSecretYour Saperly API key (sk_live_... or sk_test_...). Get one at https://saperly.com/portal — 500 free credits on signup.
SAPERLY_BASE_URLOverride the Saperly API base URL. Optional — only set for local dev or staging environments.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@saperly/mcp0.1.2

Tools

30

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
modeenumNotext = S2T+T2S via webhook, audio = raw websocket. defaults to text.text | audio
namestringYesdisplay name for the line (e.g. 'support bot')
voicestringNoTTS voice id. use saperly_list_voices to see options.
webhookUrlstringNorequired for text mode. your server receives transcribed text here.
beginMessagestringNofirst thing the agent says when a call connects.
contextLimitnumberNoconversation memory in turns (1-50). default 20.
systemPromptstringNosystem prompt for hosted mode. tells the AI agent how to behave.
audioHandlerUrlstringNorequired for audio mode. websocket URL for raw audio streaming.
recordingEnabledbooleanNoenable call recording for this line.
statusCallbackUrlstringNooptional. receives call lifecycle events.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.