sinch-engage
A Model Context Protocol (MCP) server for Sinch Engage (EU) and Sinch MessageMedia (AU). Enables AI agents to use tools for sending messages, managing contacts, and retrieving reports.
claude mcp add --transport stdio messagemedia-sinch-engage-mcp-server npx -y @sinch-engage/mcp-server \ --env MCP_TOOL_MODES="read, write, delete" \ --env MCP_TOOL_CATEGORIES="reporting, contacts, messaging" \ --env SINCH_ENGAGE_REGION="<region>" \ --env SINCH_ENGAGE_API_KEY="<your-key>" \ --env SINCH_ENGAGE_API_SECRET="<your-secret>"
How to use
The Sinch Engage MCP Server exposes Sinch Engage APIs as MCP tools, enabling you to send SMS messages, as well as generate detailed and summary reports and manage contact groups. Available tools include sendMessage for messaging, getDetailedMessageReport, getSummaryMessageReport, getSummaryInsightMessageReport, getAsyncReportStatus, getAsyncReportFields, requestAsyncDetailedMessageReport for reporting, and getContactGroups, getContactGroupDetails, getContactWithSearch, createContactGroup, createContact, updateContact, deleteContactGroup for contacts. All phone numbers must be in E.164 format. To use the server, configure it in your MCP client (e.g., Claude Desktop) and provide Sinch Engage credentials via environment variables. The server will route tool calls to Sinch Engage APIs under the hood, handling authentication and API interactions. Ensure you set MCP_TOOL_CATEGORIES to include the tools you want available (e.g., messaging, reporting, contacts) and MCP_TOOL_MODES to reflect required permissions (read, write, delete).
How to install
Prerequisites:
- Node.js v16 or newer
- npm (comes with Node.js)
- A Sinch Engage account with API credentials (API Key and API Secret)
Option A: Run via npx (recommended when using the MCP configuration example)
- Ensure Node.js and npm are installed.
- Use your MCP configuration (see mcp_config) which runs the MCP server with npx:
# No global install needed if using the provided configuration
Option B: Install the MCP server package locally and run directly
- Install Node.js (v16+).
- Install the package globally or in your project:
# Global install (alternative)
npm install -g @sinch-engage/mcp-server
# Or local install
npm install @sinch-engage/mcp-server
- Run the server using your preferred method (see configuration example) and ensure environment variables are set, e.g., in a container or shell:
export SINCH_ENGAGE_API_KEY=<your-key>
export SINCH_ENGAGE_API_SECRET=<your-secret>
export SINCH_ENGAGE_REGION=<region>
export MCP_TOOL_CATEGORIES="reporting, contacts, messaging"
export MCP_TOOL_MODES="read, write, delete"
# Start server according to your setup (e.g., with node or via npx as shown in the config)
- Configure Claude Desktop or your MCP client with the provided configuration snippet, substituting credentials and region.
Additional notes
Tips:
- Always use E.164 formatted numbers for messaging (e.g., +61400000000).
- The available region values are EU and AU as indicated; set SINCH_ENGAGE_REGION accordingly.
- Restrict MCP_TOOL_CATEGORIES and MCP_TOOL_MODES to the minimum required for your use case to reduce context size.
- If you encounter authentication errors, double-check API key/secret and region configuration.
- Ensure network access to Sinch Engage API endpoints from the environment running the MCP server.
- The CLI or MCP client configuration should map tool calls to the corresponding Sinch Engage API actions; verify tool capabilities match your permissions and plan.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.