Thruai Voice Agent Server
@mgWellPay
关于 Thruai Voice Agent Server
Give your AI agent a phone number with one API call. ThruAI provides voice, telephony, knowledge base (RAG), self-learning, and 14 integrations. 50+ MCP tools for agents to make and receive phone calls, manage conversations, and access analytics.
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"thruai": {
"command": "npx",
"args": [
"-y",
"github:mgWellPay/thruai-mcp-server"
],
"env": {
"THRUAI_API_KEY": "<YOUR_API_KEY>"
}
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Thruai Voice Agent Server?
Thruai Voice Agent Server is a Model Context Protocol (MCP) server that enables AI assistants like Claude and GPT to discover and use ThruAI's voice AI platform. It provides 50+ tools for creating voice agents, making calls, managing telephony, building workflows, and analyzing usage.
How to use Thruai Voice Agent Server?
Run directly with npx using the command THRUAI_API_KEY=sk_live_... npx github:mgWellPay/thruai-mcp-server. Alternatively, install globally or locally via npm. Configure by setting the THRUAI_API_KEY environment variable; optionally set THRUAI_BASE_URL for custom endpoints during the beta period.
Key features of Thruai Voice Agent Server
- One‑command quick start for a voice agent with phone number
- Full CRUD for voice agents (S2S or traditional pipeline)
- Outbound calls from agents to any phone number
- Usage and cost analytics with component breakdown
- Telephony: search, provision, and assign phone numbers
- Workflows with 30+ node types (CRM, calendar, email, etc.)
Use cases of Thruai Voice Agent Server
- Create a customer support voice agent with a local phone number
- Make outbound sales calls to a lead list and qualify prospects
- Analyze call transcripts, duration, cost, and AI insights
- Build complex automation workflows integrating CRM, email, and web tools
- Launch outbound calling campaigns with automated contact management
FAQ from Thruai Voice Agent Server
What API key is required?
A ThruAI API key starting with sk_live_ from your ThruAI account Settings → API Keys is required. Set it as the THRUAI_API_KEY environment variable.
How do I install the server?
The recommended method is to run with npx: THRUAI_API_KEY=sk_live_... npx github:mgWellPay/thruai-mcp-server. You can also install globally with npm install -g and run thruai-mcp.
Is ThruAI still in beta?
Yes. ThruAI is in active development, and the default API endpoint (api.thru.ai) may require a custom base URL during the beta. Set THRUAI_BASE_URL in your environment if needed.
What tools does the server expose?
Over 50 tools organized into domains: quick start, agent management, calls, telephony, workflows, campaigns, webhooks, custom tools, analytics, provider discovery, feedback, and schema discovery.
How does authentication work?
Authentication is via an API key passed as the THRUAI_API_KEY environment variable. All API calls are authorized against that key. Webhooks support optional HMAC signature verification.
AI 与智能体 分类下的更多 MCP 服务器
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
MCP-LLM Bridge
patruffBridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Shell and Coding agent for Claude and other mcp clients
rusiaamanShell and coding agent on mcp clients
评论