Using AI tools with Conversation API's RCS channel

Copy

• Copy for LLM

  Copy page as Markdown for LLMs
• View as Markdown

  Open this page as Markdown
• Open in ChatGPT

  Get insights from ChatGPT
• Open in Claude

  Get insights from Claude
• Connect to Cursor

  Install MCP server on Cursor
• Connect to VS Code

  Install MCP server on VS Code

You can use various AI tools to facilitate the generation of code that you can use to send RCS messages.

While there are any number of ways to make use of AI tools, we provide guidance on the following methods:

• Using Sinch's documentation MCP server to generate code samples
• Using an LLM to ingest Sinch's documentation and generate code samples

Note that, after your AI tool generates a code sample, you must modify it and provide your account, solution, and recipient-pecific information.

Prerequisites

In order to send an RCS message using the information in this guide, you must first:

1. Gain access to Sinch's Conversation API and create an access key and secret.
2. Create a Conversation API app.
3. Add the RCS channel to your Conversation API app. The guide linked in this step describes how to create an RCS agent. Note that, if you want to test your RCS capabilities without launching the agent (i.e., use the RCS agent in "test" mode prior to launch), you must add your intended recipient's phone number as a test number. This process is described in the linked guide.

Once you've completed the above prerequisites, ensure you collect the following information. You'll need this information to modify any sample code provided by your AI tool(s):

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 availabe to your system that facilitate endpoint identification, information lookups, and general context-setting.

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:

Connecting to the MCP server

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

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:

{
  "mcpServers": {
    "sinch-mcp": {
      "url": "https://developers.sinch.com/mcp"
    }
  }
}

Generating code samples using the MCP server

You can use Sinch's documentation MCP server to generate code snippets for your solution. To do so, enter the following prompt after installing the Sinch documentation MCP server:

Generate {YOUR_language} code to send an RCS {YOUR_message_type} message. For authentication, use {BASIC_or_OAUTH2.0}. My app is based in the {REGION_of_YOUR_APP}. {YOUR_additional_instructions}.

For example:

Generate Python code to send an RCS carousel message. For authentication, use basic auth (with access key + secret). My app is based in the EU. The cards should have an open URL action, pointing at sinch.com, that should open in a tall webview. For images, use this: https://sinch.com/wp-content/uploads/2025/03/SI-Photo-RCS-Playbook-Hands.png

Using an LLM to ingest Sinch's documentation

When using an LLM with Sinch's documentation site, provide the appropriate context in order to ensure that the LLM provides the best response to your prompt. To use your LLM of choice with Sinch's Conversation API Open API Spec, enter the following prompt:

Using this schema: https://developers.sinch.com/_bundle/docs/conversation/api-reference/conversation.yaml?download generate {YOUR_language} code to send an RCS {YOUR_message_type} message. For authentication, use {BASIC_or_OAUTH2.0}. My app is based in the {REGION_of_YOUR_APP}. {YOUR_additional_instructions}.

For example,

Using this schema: https://developers.sinch.com/_bundle/docs/conversation/api-reference/conversation.yaml?download generate Python code to send an RCS carousel message. For authentication, use basic auth (with access key + secret). My app is based in the EU. The cards should have an open URL action, pointing at sinch.com, that should open in a tall webview. For images, use this: https://sinch.com/wp-content/uploads/2025/03/SI-Photo-RCS-Playbook-Hands.png

Modifying the generated code samples

Regardless of the method you use to generate your code, you must modify it to include your account, solution, and recipient-specific values.

The values that most commonly must be modified or provided are described in the table below: