GitHub
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
Description from the maker (original English)
Official TypeScript library for the Telnyx API
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
TELNYX_API_KEYValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"telnyx": {
"command": "npx",
"args": [
"-y",
"telnyx"
],
"env": {
"TELNYX_API_KEY": "your-value"
}
}
}
}Run this in your terminal
claude mcp add telnyx --env TELNYX_API_KEY=your-value -- npx -y telnyxFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"telnyx": {
"command": "npx",
"args": [
"-y",
"telnyx"
],
"env": {
"TELNYX_API_KEY": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"telnyx": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"telnyx"
],
"env": {
"TELNYX_API_KEY": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account team-telnyx, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: TELNYX_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (6.29.3) reached the registry 7 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: GitHub, Desktop Commander, Cloudflare MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
MCP server for terminal commands, file operations, and process management
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
))](https://npmjs.org/package/telnyx)
This library provides convenient access to the Telnyx REST API from server-side TypeScript or JavaScript.
The full API of this library can be found in api.md.
It is generated with Stainless.
Use the Telnyx MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application.
Note: You may need to set environment variables in your MCP client.
npm install telnyx
The full API of this library can be found in api.md.
import Telnyx from 'telnyx';
const client = new Telnyx({ apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted });
const response = await client.calls.dial({ connection_id: 'conn12345', from: '+15557654321', to: '+15551234567', webhook_url: 'https://your-webhook.url/events', });
console.log(response.data);
Runnable examples are available for:
const { data: availableNumbers } = await client.availablePhoneNumbers.list({
filter: { country_code: 'US', national_destination_code: '312', limit: 1, }, });
const phoneNumber = availableNumbers?.[0]?.phone_number; if (!phoneNumber) throw new Error('No phone numbers found');
const { data: order } = await client.numberOrders.create({ phone_numbers: [{ phone_number: phoneNumber }], });
const { data: message } = await client.messages.send({
from: '+15551234567', to: '+15557654321', text: 'Hello from Telnyx!', });
const { data: call } = await client.calls.dial({
connection_id: 'your-connection-id', from: '+15551234567', to: '+15557654321', webhook_url: 'https://example.com/webhooks', });
Configure the client with your Telnyx public key and pass the exact raw request body to unwrap. Parsing or re-serializing the body before verification invalidates the signature.
const webhookClient = new Telnyx({
apiKey: process.env['TELNYX_API_KEY'], publicKey: process.env['TELNYX_PUBLIC_KEY'], });
const event = webhookClient.webhooks.unwrap(rawBody, { headers: requestHeaders, });
See the complete Express webhook verification example for raw-body handling and error responses.
A WebRTC client logs in with a token for a telephony credential. Instead of asking the API for one per login (createToken), your backend can sign it itself from the credential's token_material, with no request to Telnyx per token:
// Once, when the user is set up: create the credential and ask for the signing material.
const { data: credential } = await client.telephonyCredentials.create({ connection_id: '1234567890', include: 'token_material', }); // Store these with the user, server side: the token is built from all of them. await db.save(userId, { id: credential.id, user_id: credential.user_id, sip_username: credential.sip_username, expires_at: credential.expires_at, token_material: credential.token_material, });
// On every login, with no request to Telnyx: const loginToken = await client.telephonyCredentials.toJwt(credential, { ttl: 3600 }); // or later, from the stored values: const loginTokenFromStore = await client.telephonyCredentials.toJwt(await db.load(userId), { ttl: 3600 });
The API returns token_material only when include: 'token_material' is passed. For a credential created without it, or retrieved later, toJwt fetches the material once with retrieveTokenMaterial. token_material is as sensitive as the SIP password: keep it on the server. See the WebRTC login token example.
Connection failures and retryable HTTP responses are retried twice by default. Set maxRetries for the client or override it for an individual request:
const retryingClient = new Telnyx({
apiKey: process.env['TELNYX_API_KEY'], maxRetries: 4, });
await retryingClient.messages.send( { from: '+15551234567', to: '+15557654321', text: 'Hello from Telnyx!', }, { maxRetries: 0 }, );
See Handling errors and Retries for details.
This library includes TypeScript definitions for all request params and response fields. You may import and use them like so:
import Telnyx from 'telnyx';
const client = new Telnyx({ apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted });
const params: Telnyx.NumberOrderCreateParams = { phone_numbers: [{ phone_number: '+15558675309' }], }; const numberOrder: Telnyx.NumberOrderCreateResponse = await client.numberOrders.create(params);
Documentation for each method, request param, and response field are available in docstrings and will appear on hover in most modern editors.
Request parameters that correspond to file uploads can be passed in many different forms:
File (or an object with the same structure)fetch Response (or an object with the same structure)fs.ReadStreamtoFile helperimport fs from 'fs';
import Telnyx, { toFile } from 'telnyx';
const client = new Telnyx();
// If you have access to Node fs we recommend using fs.createReadStream(): await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2', file: fs.createReadStream('/path/to/file'), });
// Or if you have the web File API you can pass a File instance: await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2', file: new File(['my bytes'], 'file'), });
// You can also pass a fetch Response: await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2', file: await fetch('https://somesite/file'), });
// Finally, if none of the above are convenient, you can use our toFile helper: await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2', file: await toFile(Buffer.from('my bytes'), 'file'), }); await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2', file: await toFile(new Uint8Array([0, 1, 2]), 'file'), });
When the library is unable to connect to the API, or if the API returns a non-success status code (i.e., 4xx or 5xx response), a subclass of APIError will be thrown:
const numberOrder = await client.numberOrders
.create({ phone_numbers: [{ phone_number: '+15558675309' }] }) .catch(async (err) => { if (err instanceof Telnyx.APIError) { console.log(err.status); // 400 console.log(err.name); // BadRequestError console.log(err.headers); // {server: 'nginx', ...} } else { throw err; } });
Error codes are as follows:
| Status Code | Error Type |
|---|---|
| 400 | BadRequestError |
| 401 | AuthenticationError |
| 403 | PermissionDeniedError |
| 404 | NotFoundError |
| 422 | UnprocessableEntityError |
| 429 | RateLimitError |
| >=500 | InternalServerError |
| N/A | APIConnectionError |
Certain errors will be automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, and >=500 Internal errors will all be retried by default.
You can use the maxRetries option to configure or disable this:
// Configure the default for all requests:
const client = new Telnyx({ maxRetries: 0, // default is 2 });
// Or, configure per-request: await client.numberOrders.create({ phone_numbers: [{ phone_number: '+15558675309' }] }, { maxRetries: 5, });
Requests time out after 1 minute by default. You can configure this with a timeout option:
// Configure the default for all requests:
const client = new Telnyx({ timeout: 20 * 1000, // 20 seconds (default is 1 minute) });
// Override per-request: await client.numberOrders.create({ phone_numbers: [{ phone_number: '+15558675309' }] }, { timeout: 5 * 1000, });
On timeout, an APIConnectionTimeoutError is thrown.
Note that requests which time out will be retried twice by default.
List methods in the Telnyx API are paginated. You can use the for await … of syntax to iterate through items across all pages:
async function fetchAllAccessIPAddressResponses(params) {
const allAccessIPAddressResponses = []; // Automatically fetches more pages as needed. for await (const accessIPAddressResponse of client.accessIPAddress.list({ 'page[number]': 1, 'page[size]': 50, })) { allAccessIPAddressResponses.push(accessIPAddressResponse); } return allAccessIPAddressResponses; }
Alternatively, you can request a single page at a time:
let page = await client.accessIPAddress.list({ 'page[number]': 1, 'page[size]': 50 });
for (const accessIPAddressResponse of page.data) { console.log(accessIPAddressResponse); }
// Convenience methods are provided for manually paginating: while (page.hasNextPage()) { page = await page.getNextPage(); // ... }
Only the beginning is shown; read the rest in the repo