Customer success
Drafts for every new G2, Trustpilot and app-store review: thanks for the good ones, a fix-first answer for the bad ones.
Copy it into your agent, replace the parts in braces, and save it as a recurring task.
Use the Soundev MCP tools.
1. Call search_mentions with tags ["review"], keyword types ["brand"], engaged false, since {yesterday's date}.
2. Sort by rating, lowest first.
3. For each review, call get_mention and draft a reply of at most 60 words from {name, role} at {company}:
- 1-2 stars: thank them, name the specific problem, say what you will do, offer {support email}
- 3 stars: thank them and address the main point
- 4-5 stars: thank them for something specific they said
4. Return: platform, rating, link, draft. I will post them and mark them handled.Add Soundev as an MCP server in Claude, ChatGPT, Cursor or any MCP client, then sign in when it asks. The address is:
https://soundev.com/api/mcp
Clients without sign-in can use an API key instead (Settings → API keys). Setup details