Skip to content

Using AI tools with Conversation API

Note:

This guide includes best practices for using generative AI tools with Sinch's Conversation API. Generative AI can make mistakes, and Sinch has limited influence over the output of any given generative AI tool. Ensure you review any code produced by generative AI to confirm its accuracy, stability, and security against our documentation, your environment, and your needs.

You can use AI tools to facilitate the generation of code that you can use with Sinch's Conversation API.

In the sections below, we provide guidance on how LLMS, AI tools, and AI agents can consume and navigate our documentation using several different methods.

Using the llms.txt page to navigate Sinch's developer documentation

If you are using an AI tool, LLM, or agent to navigate our documentation site, you can visit our llms.txt page (located at https://developers.sinch.com/llms.txt) for a map of all the documentation files for Sinch.

This page is in plaintext, and it provides the title of each page, a description, and a link to the Markdown version of the page for easy LLM consumption and analysis.

Viewing Markdown versions of Sinch's developer documentation

Most pages on Sinch's developer documentation site has a Markdown counterpart.

The Markdown version of the page is in plaintext, making it easier for AI tools, LLMs, and agents to consume the contents.

To access the Markdown version of a page, simply append .md to the end of the URL. For example, to access the Markdown version of this page, simply add .md to the end of the URL in the address bar.

Additional examples are provided in the table below:

Page URLMarkdown version
https://developers.sinch.com/docs/conversation/getting-startedhttps://developers.sinch.com/docs/conversation/getting-started.md
https://developers.sinch.com/docs/voice/getting-startedhttps://developers.sinch.com/docs/voice/getting-started.md
https://developers.sinch.com/docs/in-app-calling/getting-startedhttps://developers.sinch.com/docs/in-app-calling/getting-started.md
https://developers.sinch.com/docs/est/getting-startedhttps://developers.sinch.com/docs/est/getting-started.md
https://developers.sinch.com/docs/numbers/getting-startedhttps://developers.sinch.com/docs/numbers/getting-started.md

For a complete directory of Markdown pages, see our llms.txt page.

Using Sinch's documentation MCP server

In order to generate code samples using AI tools, you may connect directly to Sinch's documentation MCP server. This will make several tools available to your system that facilitate endpoint identification, information lookups, and general context-setting.

Note:

Sinch's documentation MCP server provides tools that help you navigate Sinch's documentation. Because Sinch's documentation includes various code samples, it can also help you generate code samples. It will not make calls to the identified endpoints for you; you must include any provided code in your solution and customize it to correctly reference your account and credentials.

The tools are described in the table below. Note that, while you may not have to explicitly call out these tools when designing your prompt (or using the prompts we provide later in this document), you must still ensure the tools are activated in whatever AI environment you work in:

ToolParametersDescription
whoamiNoneReturns information about the authenticated user.
list-apisname?: stringLists available APIs with their context and purpose.
get-endpointsname: stringReturns all endpoints and their descriptions for a specific API.
get-endpoint-infoname: string``path: string``method: stringReturns comprehensive information about a specific endpoint, including parameters, security, and examples.
get-security-schemesname: string``path: string``method: stringGets the security schemes for a specific API.
get-full-api-descriptionname: stringReturns the complete OpenAPI description.
searchquery: stringSearches documentation and returns relevant content for a query.

Connecting to the MCP server

You may connect to our documentation MCP server by clicking the Connect MCP button:

Note:

The AI tools listed in the Connect MCP button drop-down list and the tools described below are for illustrative purposes. You may use our documentation MCP server with any AI tool that can connect to MCP servers.

Alternatively, copy the following URL and add it to your AI tool: https://developers.sinch.com/mcp. Some examples of how to add the Sinch documentation MCP server tools to your AI solution are detailed in the tabs below:

Connect Cursor to the MCP server

  1. In Cursor, open the command palette.
  • macOS: Command + Shift + P
  • Windows/Linux: Ctrl + Shift + P
  1. Type "Open MCP settings" in the command palette.
  2. Select "Add custom MCP".

Cursor opens the mcp.json file.

Configure the MCP server

  1. In mcp.json, add your server configuration:
{
  "mcpServers": {
    "sinch-mcp": {
      "url": "https://developers.sinch.com/mcp"
    }
  }
}
  1. Save the mcp.json file.
  2. Return to MCP settings and confirm the connection.

If authentication is required, select Needs login and complete the sign-in flow. After connecting, Cursor displays the list of available tools.

Test the Cursor connection

In Cursor chat (Agent mode), ask a question that triggers an MCP tool.

Using Sinch's skills to streamline AI usage

Skills files (or "skills") provide AI-specific guidance, hints, troubleshooting tips, and use-case information that can help your AI agents better understand various topics. They are especially helpful when using AI tools and agents in coding environments.

Sinch provides skills that help your AI solution navigate our documentation, generate code samples, and perform API calls.

To view Sinch's skills files, visit the Sinch Skills GitHub repo. The sub-sections below provide concise installation, usage, and structural information. For a more thorough explanation of Sinch Skills, see our dedicated developer document on Sinch Skills.

Installing Sinch skills

To make use of our skills files, you must install them in your coding environment. Information on ways to install Sinch's skills files are included on the tabs below:

Installing Sinch's skills using NPM

To install Sinch skills using NPM:

  1. Open your preferred IDE and navigate to the directory or repo in which you project is stored.
    Note:

    Alternatively, you may navigate to your home directory to install Sinch's skill files. They will then be available for use across various coding projects.

  2. Open a terminal and/or command prompt.
  3. Run the command npx skills add sinch/skills.

Using Sinch skills

Once Sinch's skills have been installed, your AI tool or agent should make use of them automatically. AI tools and agents will consult the skills files whenever you make a request.

Sinch skills structure

Each skill lives in its own folder under skills/. The SKILL.md file contains YAML frontmatter (name and description) and markdown sections including Overview, Getting Started, Key Concepts, Common Patterns, Gotchas & Best Practices, and Links sections.

skills/
  <product>/
    SKILL.md            # Main skill file (required)
    scripts/            # Optional helper scripts
    references/         # Optional detailed reference material
    assets/             # Optional images or other assets

IDE extensions and plugins

Sinch has developed several plugins and extensions for AI developer tools. These extensions and plugins help AI streamline code creation using Sinch's APIs.

The extensions, plugins, related artifacts, and installation instructions can be found in the corresponding IDE marketplaces, extension registries, and code repositories. The supported tools are linked below:

ToolDescription
Bundles the Sinch Build skills catalog with the hosted Sinch Docs MCP server. Codex can search authoritative Sinch developer documentation and follow product guides for Conversation API (SMS, RCS, WhatsApp), Voice, Verification, Numbers, Number Lookup, 10DLC, Elastic SIP Trunking, Fax, Mailgun, Provisioning, and Authentication. Documentation search requires no credentials. Optional bundled scripts can call live Sinch APIs, such as sending a test message or managing webhooks, using your own Sinch credentials and only with your approval; these calls may incur charges.
This VS Code extension supports multiple Sinch and Mailgun products:
  • Sinch Conversation API - One simple API to reach customers over multiple channels and deliver a mobile-first experience that's out of this world!
  • Sinch Number Validation - Validate phone numbers in real-time to ensure deliverability and reduce costs.
  • Mailgun Email Validation - Validate email addresses (single and bulk) to improve email deliverability and maintain sender reputation.
This Open VSX extension supports multiple Sinch and Mailgun products:
  • Sinch Conversation API - One simple API to reach customers over multiple channels and deliver a mobile-first experience that's out of this world!
  • Sinch Number Validation - Validate phone numbers in real-time to ensure deliverability and reduce costs.
  • Mailgun Email Validation - Validate email addresses (single and bulk) to improve email deliverability and maintain sender reputation.
This JetBrains plugin supports the following Sinch products:
  • Sinch Conversation API - One simple API to reach customers over multiple channels and deliver a mobile-first experience that's out of this world!
  • Mailgun - Email validation and delivery service for verifying addresses and ensuring reliable email communication.
This Cursor plugin contains skills for various Sinch products, commands to set up MCP, send messages, retrieve senders, list webhooks, create webhooks, update webhooks, delete webhooks, view webhook trigger lists, and view help information. An MCP JSON file is also provided here.
A Kiro Power that connects the Sinch Build platform to your AI-assisted development workflow — send SMS, WhatsApp, and RCS messages, verify phone numbers, make voice calls, and manage virtual numbers without leaving your IDE. More information can be found at the Sinch Kiro Power repo.
This repository contains Sinch plugins and related artifacts for AI developer tools. The repository supports:
  • A Claude Code plugin that integrates the Sinch Conversation API, allowing you to send SMS messages, manage webhooks, and inspect your Sinch configuration directly from your terminal. This plugin includes the Sinch Build MCP (sinch) and the Sinch Docs MCP (sinch-docs).
  • A Cursor IDE plugin that integrates the Sinch Conversation API, allowing you to send SMS and RCS messages, manage webhooks, and interact with your Sinch configuration directly from Cursor IDE. This plugin includes the Sinch Build MCP (sinch) and the Sinch Docs MCP (sinch-docs).
  • A Gemini CLI extension that integrates the Sinch Conversation API, allowing you to send SMS messages, manage webhooks, and interact with your Sinch configuration directly from Gemini CLI. This extension includes the Sinch Build MCP (sinch) and the Sinch Docs MCP (sinch-docs via httpUrl).
  • An Antigravity CLI plugin that integrates the Sinch Conversation API and related products. This is the native Antigravity successor to the Gemini CLI extension above; both remain available.
  • A Codex plugin that bundles the Sinch Build skills catalog with the hosted, no-auth Sinch Docs MCP. It is read-only: Codex can search Sinch developer documentation and follow product guides.