Skip to main content
Glama
ClickSend MCP Server

ClickSend MCP Server

by J-Gal02

ClickSend MCP Server

A Model Context Protocol (MCP) server that provides SMS messaging and Text-to-Speech (TTS) call capabilities through ClickSend's API. This server enables AI models to send SMS messages and initiate voice calls programmatically.

Features

  • SMS Messaging: Send SMS messages to any phone number worldwide

  • Text-to-Speech Calls: Make voice calls with customizable text-to-speech messages

  • Rate Limiting: Built-in protection with 5 actions per minute limit

  • Input Validation: Comprehensive validation for phone numbers and message content

  • Error Handling: Detailed error messages and proper error propagation

Related MCP server: Slack MCP Server

Installation

Prerequisites

  • Node.js (v16 or higher)

  • ClickSend account with API credentials

  • MCP-compatible Client

Setup

  1. Clone the repository:

git clone https://github.com/J-Gal02/clicksend-mcp.git
cd clicksend-mcp
  1. Install dependencies:

npm install
  1. Build the project:

npm run build

Setting up the MCP Client

Add the following sections into your cline_mcp_settings.json file or claude_desktop_config.json file.

Be sure to replace the directory with the correct path to the build folder, as shown in the example below, as well as the username and API key with your own.

{
    "mcpServers": {
        "clicksend": {
            "command": "node",
            "args": ["/directory/to/build/folder/clicksend-mcp/build/index.js"],
            "env": {
                "CLICKSEND_USERNAME": "example@droove.net",
                "CLICKSEND_API_KEY": "ZZZZZZZZ-YYYY-YYYY-YYYY-XXXXXXXXXXXX"
            }
        }
    }
}

Usage

Available Tools

1. send_sms

Send SMS messages to specified phone numbers.

Parameters:

  • to: Phone number in E.164 format (e.g., +61423456789)

  • message: Text content to send

Example:

{
  "name": "send_sms",
  "arguments": {
    "to": "+61423456789",
    "message": "Hello from ClickSend MCP!"
  }
}

2. make_tts_call

Initiate Text-to-Speech calls.

Parameters:

  • to: Phone number in E.164 format

  • message: Text content to convert to speech

  • voice: Voice type ('female' or 'male', defaults to 'female')

Example:

{
  "name": "make_tts_call",
  "arguments": {
    "to": "+61423456789",
    "message": "This is a Text-to-Speech call from ClickSend MCP",
    "voice": "female"
  }
}

Rate Limiting

The server implements a rate limit of 5 actions per minute to prevent abuse. Requests exceeding this limit will receive an error response with a retry delay suggestion.

Development

Available Scripts

  • npm run build: Compile TypeScript and make the output executable

  • npm run start: Start the MCP server

  • npm run dev: Run TypeScript compiler in watch mode

Project Structure

clicksend-mcp/
├── src/
│   ├── index.ts        # Main server implementation
│   ├── client.ts       # ClickSend API client
│   └── utils/
│       └── validation.ts # Input validation utilities
├── build/              # Compiled JavaScript output
└── package.json        # Project configuration

Error Handling

The server provides detailed error messages for various scenarios:

  • Invalid phone numbers

  • Message content validation failures

  • Rate limit exceeded

  • API authentication errors

  • Network connectivity issues

Error responses include appropriate error codes and descriptive messages to help diagnose issues.

TODO

  • Multiple Recepients

  • Configure Sender IDs

  • SMS

  • TTS

  • Email

  • Media Uploading

    • Email Attachments

    • MMS

    • Letters

    • Postcards

    • Fax

  • Cost Calculation and Confirmation

  • Statistics

  • History

  • Contacts

  • Automations

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Available Tools

2 tools
make_tts_callC

Make Text-to-Speech calls via ClickSend

Inputs: to (required), message (required), voice.

send_smsC

Send SMS messages via ClickSend

Inputs: to (required), message (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one handles text-to-speech calls and the other handles SMS messaging. There is no overlap in functionality, and an agent can easily differentiate between them based on their names and descriptions.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern (make_tts_call and send_sms), using clear action verbs ('make' and 'send') followed by specific nouns. The naming is predictable and readable throughout the set.

    Tool Count2/5

    With only two tools, the server feels thin for a communications platform like ClickSend, which might be expected to support more operations such as checking SMS status, managing contacts, or handling voice calls. The scope appears limited, potentially causing gaps in agent workflows.

    Completeness2/5

    For a ClickSend server, there are significant gaps in coverage: it lacks tools for checking delivery status of SMS or TTS calls, managing contacts, viewing message history, or handling other communication types like email or fax. This incomplete surface will likely lead to agent failures in broader communication tasks.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that enables Claude and other AI assistants to send SMS and MMS messages using Twilio.
      19 npm
      15
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      A server implementing Model Context Protocol that enables AI assistants to interact with Slack API through a standardized interface, providing tools for messaging, channel management, user information retrieval, and more.
      11
      110
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      A server that enables AI assistants to interact with the Omnisend marketing platform, supporting contact management, product management, and event tracking operations through natural language.
      17
      1
      Apache 2.0
    • F
      license
      Not graded
      quality
      D
      maintenance
      A simple server that enables AI models to send WhatsApp messages via the Twilio API by exposing a send\_whatsapp tool through the FastMCP framework.
      1
      -