Score what your Claude agent says to customers.
Teams building support agents on Anthropic’s platform need a way to know when the agent gets it wrong before a customer does. Supportman reviews each reply against a support QA rubric and returns a structured verdict.
Connect it as a remote MCP server: your agent sends a draft or a finished conversation, Supportman returns a score, a predicted CSAT, message-level comments and a suggested rewrite.
Supportman for Anthropic is in early preview. The demo is open now, no account needed.
Connect the demo in under a minute.
The demo server is open to anyone. Its reviews are rule-based: instant, free, nothing stored, and no AI on our side. It works in any assistant or agent that lets you add a custom MCP server.
https://supportman.io/mcp
- Step 1
Add https://supportman.io/mcp as a custom connector (MCP server) in Anthropic. If it asks about sign-in, choose no authentication.
- Step 2
Ask: “Show me a sample Supportman review.”
- Step 3
Paste a real thread, an email chain or a reply you are about to send, and ask Supportman to review it.
From Claude Code:
claude mcp add --transport http supportman-demo https://supportman.io/mcp
A code review, for support replies.
Paste or point at any conversation: a Gmail thread, a Slack thread, a helpdesk transcript. Supportman scores it on the same four categories it already uses for AI conversation scoring in Intercom, then tells you exactly what to change. Example below.
The thread you paste
Customer
My order arrived broken. This is the second time. I want a refund.
Agent
Hi, please send a photo of the item and your order number and we will look into it.
Supportman review
69/100 · predicted CSAT 2/5
- Brand voice & tone16/20
- Knowledge & accuracy24/30
- Resolution & helpfulness14/30
- Communication efficiency15/20
- No acknowledgement that this is the second broken order. Lead with that.
- Asks for the order number, which is already on the conversation.
- No outcome offered. Say what happens once the photo arrives.
Suggested reply · I'm sorry, a second broken order is not okay. Send a photo when you can and I'll refund you the same day, no need to return it.
- “Check this draft against our support rubric before replying.”
- “Score these 50 test conversations and compare to yesterday’s run.”
- “Flag any reply with a predicted CSAT under 3.”
Supportman in Anthropic, one sign-in.
Agents built on the Claude API
Claude can call remote MCP servers as tools, so a support agent can ask Supportman to check its own draft before sending.
Claude Code
Score a batch of transcripts from your terminal while you iterate on an agent’s prompt.
Self-check before send
The agent reviews its own draft with Supportman and revises if the score is low.
Eval set for support agents
A rubric built for support, not a generic helpfulness score, to compare prompt and model changes.
Human handoff signal
Route a conversation to a person when the predicted CSAT drops, not after the rating lands.
Supportman for Anthropic, answered.
Is this an Anthropic product?
No. Supportman is independent and connects through the open Model Context Protocol (MCP).
What does the review return?
Structured JSON: four category scores, a 0–100 total, a 1–5 predicted CSAT, comments anchored to messages, and a suggested reply.
Is this available today?
A free demo is: add https://supportman.io/mcp to your assistant as a custom MCP server, no account needed. Its reviews are rule-based. The full product, with AI scoring and your Intercom data, is in early preview: request access and we will add you as we open it up, platform by platform.
What does a review score?
The same four categories Supportman already uses for AI conversation scoring in Intercom: brand voice and tone (20), knowledge and accuracy (30), resolution and helpfulness (30), and communication efficiency (20). You get a 0–100 quality score, a predicted CSAT from 1 to 5, line-level comments, and a suggested better reply.
Do I need Intercom to use it?
Not for reviewing a pasted conversation. Connecting an Intercom workspace adds the second half: asking about your real CSAT, DSAT conversations, Fin, and agent performance.
Supportman for Anthropic is in early preview.
Request access and we will let you in as we open the preview up. Already a Supportman customer? Use your work email and we will prioritise your workspace.
Anthropic is a trademark of Anthropic. Supportman is an independent product, not made by, endorsed by or affiliated with Anthropic.
Request early access
Get on the list for Supportman for Anthropic.