sinch-help

Setup instructions for connecting the Sinch Conversation API to Claude Code through environment variables. Sinch Conversation API is a service for sending and receiving messages such as SMS and RCS.

In plain words
What is it for?
Use it to find the five required environment variables and set up a Sinch Build account, Conversation API access, and an access key.
Why use it?
It explains which Sinch credentials and regional settings must be configured before the messaging connection can run.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/sinch/sinch-plugins/sinch-help
Clone the repo
git clone --depth 1 https://github.com/sinch/sinch-plugins
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,331 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.01331
Opus 5 $0.00007 $0.00665
Sonnet 5 $0.00003 $0.00266
Haiku 4.5 $0.00001 $0.00133

Measured 2d ago against content hash c22fa8851d29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

sinch-help scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

~/.claude/settings.json
plugins/sinch-claude-plugin/commands/sinch-help.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sinch Conversation API Setup

Configure the required environment variables to enable the Sinch Conversation API MCP server in Claude Code.

Overview

This plugin uses the Sinch Conversation API MCP server (defined in .mcp.json) to send and receive messages via SMS and RCS channels. It supports multiple message types (text, media, location, choice, template), batch messaging (up to 1000 recipients), template management, and channel fallback.

For more details about the underlying MCP server and tools, see Sinch MCP Server

Required Environment Variables

You need to obtain and configure the following 5 variables:

  • CONVERSATION_PROJECT_ID - Your Sinch project ID
  • CONVERSATION_KEY_ID - Your API key ID
  • CONVERSATION_KEY_SECRET - Your API key secret
  • CONVERSATION_REGION - Your Sinch region (e.g., us, eu, br)
  • CONVERSATION_APP_ID - Your Conversation app ID

Get Your Sinch Credentials

Configuration Steps

1. Open Claude Code Settings

On macOS, the settings file is located at:

~/.claude/settings.json

You can open it by:

  • Using a text editor: code ~/.claude/settings.json or open -a TextEdit ~/.claude/settings.json
  • Using Finder: Press Cmd+Shift+G and paste ~/.claude/settings.json

2. Add Environment Variables

Add or update the env section in your settings.json:

{
  "env": {
    "CONVERSATION_PROJECT_ID": "your-project-id-here",
    "CONVERSATION_KEY_ID": "your-key-id-here",
    "CONVERSATION_KEY_SECRET": "your-key-secret-here",
    "CONVERSATION_REGION": "your-app-region (e.g., us, eu, br)",
    "CONVERSATION_APP_ID": "your-app-id-here"
  }
}

Read the full file on GitHub · 134 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 134 lines · 14 tokens per session scan B c22fa8851d29

Subscribe to this mod's changes

sinch-help is a command published in the GitHub repository sinch/sinch-plugins (6 stars, last pushed 20d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,331 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.