GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Official TypeScript library for the Telnyx API
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
TELNYX_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"telnyx": {
"command": "npx",
"args": [
"-y",
"telnyx"
],
"env": {
"TELNYX_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add telnyx --env TELNYX_API_KEY=your-value -- npx -y telnyx运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"telnyx": {
"command": "npx",
"args": [
"-y",
"telnyx"
],
"env": {
"TELNYX_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"telnyx": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"telnyx"
],
"env": {
"TELNYX_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过 GitHub 账户 team-telnyx 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:TELNYX_API_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(6.29.3)于7个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:GitHub, Desktop Commander, Cloudflare MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
))](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(); // ... }
只显示了开头部分;其余内容请在仓库中阅读