What are the prerequisites to run the server?
You need Node.js (which includes npm and npx) installed on your system. The LTS version is recommended.
@saaslabsco
基本信息
The JustCall Model Context Protocol (MCP) Server lets Large Language Models (LLMs) and AI agents make real-world voice calls and send SMS directly through JustCall’s APIs — securely, contextually, and programmatically.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"justcall": {
"url": "https://mcp.justcall.host/mcp",
"headers": {
"Authorization": "Bearer <JUSTCALL_API_KEY>:<JUSTCALL_API_SECRET>"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
此服务需要认证,获取工具列表可能需要登录或使用服务提供方的凭据。
点击上方按钮,直接连接服务器端点实时获取工具列表。
JustCall MCP Server lets Large Language Models (LLMs) and AI agents make real-world voice calls and send SMS directly through JustCall’s APIs, providing a function-calling interface for conversational AI systems.
Install Node.js, then configure your MCP client (e.g., Claude Desktop) by adding the server details to its config file using your JustCall API key and secret. For remote access, connect via Streamable HTTP Transport to https://mcp.justcall.host/mcp with bearer token authentication.
You need Node.js (which includes npm and npx) installed on your system. The LTS version is recommended.
Get your JustCall API key and secret from the JustCall dashboard at `https://app.justcall.io/app/developersApiCredentials`. Include them as a bearer token in the request headers, for example `Authorization: <JUSTCALL_API_KEY>:<JUSTCALL_API_SECRET>`.
Connect to `https://mcp.justcall.host/mcp` from any MCP client using Streamable HTTP Transport, and include your JustCall API key as a bearer token.
The recommended and default transport is Streamable HTTP. You can also use the `supergateway` npx command with the `--streamableHttp` flag.
Yes, clone the repository, install dependencies with `pnpm install`, build with `pnpm run build`, and test using `pnpm run inspector`.

Model Context Protocol Servers
Painless E2E Automation for Mobile and Web
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
评论