JustCall

The JustCall MCP Server connects Large Language Models to real-world telephony through the Model Context Protocol.

This MCP server enables your AI agents to make phone calls, send text messages, and manage communications directly through JustCall’s telephony infrastructure.

Features

  • 📞 Voice call management and transcription
  • 💬 SMS messaging with contact management
  • 👥 User and agent coordination
  • 📊 Comprehensive analytics and reporting
  • 🔔 Real-time webhook notifications
  • 📱 Phone number administration
  • 📢 Sales dialer campaign automation

Use Cases

  • Automated Customer Outreach: You could build an AI agent that pulls a list of new leads from your CRM each morning. The agent then uses the send_sms tool to send a personalized introductory message to each one. This takes a manual, repetitive task off your sales team’s plate.
  • Intelligent Appointment Schedulers: An AI can manage appointment reminders. It can check a calendar, find upcoming appointments, and use the send_sms function to text a confirmation reminder. It can then use check_sms_reply to see if the person confirmed, canceled, or wants to reschedule, all without human intervention.
  • Dynamic Voice Support Menus: Instead of a static “Press 1 for sales” phone menu, you can have an LLM-powered agent that actually talks to the customer. It can use tools like get_user to look up customer information and get_call_journey to understand past interactions before deciding how to route the call.

How to Use It

Claude Desktop Setup

To get this running with Claude Desktop, you’ll need to edit its configuration file.

Open the Claude Desktop settings by pressing CMD + , (on Mac). Navigate to the Developer tab and click Edit Config. This action opens the claude_desktop_config.json file.

You will need your JustCall API Key and Secret. You can find these in your JustCall developer dashboard.

Add the following JSON block to your claude_desktop_config.json file. This tells Claude Desktop how to find and run the JustCall MCP server.

{
  "mcpServers": {
    "JustCall-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "supergateway",
        "--streamableHttp",
        "https://mcp.justcall.host/mcp",
        "--oauth2Bearer",
        "<JUSTCALL_API_KEY>:<JUSTCALL_API_SECRET>"
      ]
    }
  }
}

Remember to replace <JUSTCALL_API_KEY>:<JUSTCALL_API_SECRET> with your actual credentials. After you save the file, restart Claude Desktop for the changes to take effect.

Remote MCP Connection

If you want to connect from a different MCP client, you can use the Streamable HTTP Transport. This is the recommended method.

Your client should connect to https://mcp.justcall.host/mcp. You must include your JustCall API key and secret as a bearer token in the Authorization header.

The header format looks like this: Authorization: <JUSTCALL_API_KEY>:<JUSTCALL_API_SECRET>

Available Tools

The server comes with 29 tools:

  • Calls (5 tools): list_calls, get_call, update_call, get_call_journey, get_voice_agent_data.
  • Users & Agents (2 tools): list_users, get_user.
  • SMS & Messaging (8 tools): send_sms, list_sms, get_sms, check_sms_reply, list_sms_tags, get_sms_tag, create_sms_tag, delete_sms_tag.
  • Contacts (2 tools): list_contacts, create_contact.
  • Analytics (4 tools): get_agent_analytics, get_account_analytics, get_number_analytics, get_sales_dialer_analytics.
  • Webhooks (2 tools): list_webhooks, create_webhook.
  • Phone Numbers (2 tools): list_numbers, get_number.
  • Sales Dialer Campaigns (4 tools): list_campaigns, get_campaign, create_campaign, update_campaign.

Development

If you want to work on the server code itself, you can clone the project.

Install the dependencies.

pnpm install

Build the server.

pnpm run build

Test the server with the inspector tool.

pnpm run inspector

You would then update your claude_desktop_config.json to point to your local development server instead of the remote one.

FAQs

Q: What is the difference between the remote configuration and running it locally?
A: The remote configuration points to JustCall’s hosted MCP server (https://mcp.justcall.host/mcp), which is ready to use immediately. Running it locally is for development purposes.

Q: How does authentication work?
A: Authentication uses your JustCall API Key and Secret. You combine them into a single string separated by a colon (KEY:SECRET) and pass them as a bearer token in the Authorization header of your requests.

Q: Do I need a paid JustCall account?
A: Yes, you need an active JustCall account to generate the API credentials required to authenticate with the MCP server. The server’s functions interact directly with your JustCall account’s data and services.

Latest MCP Servers

CVE

An MCP Server that connects Claude to 27 security tools for CVE triage, EPSS checks, KEV status, exploit lookup, and package scanning.

WebMCP

webmcp is an MCP server that connects MCP clients to web search, page fetching, and local LLM-based extraction. It’s ideal…

Google Meta Ads GA4

An MCP server that connects AI assistants to Google Ads, Meta Ads, and GA4 for reporting, edits, and cross-platform analysis.

View More MCP Servers >>

Featured MCP Servers

Notion

Notion's official MCP Server allows you to interact with Notion workspaces through the Notion API.

Claude Peers

An MCP server that enables Claude Code instances to discover each other and exchange messages instantly via a local broker daemon with SQLite persistence.

Excalidraw

Excalidraw's official MCP server that streams interactive hand-drawn diagrams to Claude, ChatGPT, and VS Code with smooth camera control and fullscreen editing.

More Featured MCP Servers >>

FAQs

Q: What exactly is the Model Context Protocol (MCP)?

A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.

Q: How is MCP different from OpenAI's function calling or plugins?

A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.

Q: Can I use MCP with frameworks like LangChain?

A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.

Q: Why was MCP created? What problem does it solve?

A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.

Q: Is MCP secure? What are the main risks?

A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.

Q: Who is behind MCP?

A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.

Get the latest & top AI tools sent directly to your email.

Subscribe now to explore the latest & top AI tools and resources, all in one convenient newsletter. No spam, we promise!