The agent-native product reviews reader
Connect any AI agent to your product reviews. Pull your latest Junip reviews — newest-first, incremental since last check — through the Model Context Protocol. Filter by rating, media, or product, and poll for new reviews on a schedule without re-reading the whole backlog.
How it works
From a connected store to a stream of fresh reviews in four steps.
Sign up and get an API key
Create a free account at gentic.co, generate an API key from your dashboard, and use it as a Bearer token to authenticate your agent.
Connect Junip in your dashboard
Paste your Junip store key once in the Gentic dashboard (Integrations → Junip). It's encrypted at rest, and the Reviews server reads it automatically — your agent never has to handle the credential.
Add the MCP server to your agent
Drop https://mcp.gentic.co/reviews into Claude Code, Claude Web, OpenClaw, Claude Cowork, ChatGPT, n8n, or any MCP-compatible client. Pass your Gentic API key as a Bearer token — or connect via OAuth on clients that support it.
Read reviews — newest first, or only what's new
Ask your agent for your latest reviews. For one-off pulls, just call the tool. For scheduled polling, persist the returned latest_id and pass it back as since_id next time to fetch only reviews newer than your last check.
Available tools
1 tool your AI agent can call through the Model Context Protocol.
junip_get_reviews
Fetch reviews from Junip (v1 Display API), newest-first, with cursor pagination and incremental-since support.
Connect in seconds
Sign up, connect Junip in your dashboard, grab your API key, and add the MCP server to your agent. Works with Claude Code, Claude Web, OpenClaw, Claude Cowork, ChatGPT, n8n, and any MCP client.
claude mcp add gentic-reviews \
--transport http \
https://mcp.gentic.co/reviews \
--header "Authorization: Bearer YOUR_API_KEY"You can also connect via OAuth — just add gentic-reviews as a connector in Claude or ChatGPT settings. No API key needed; authentication is handled automatically.
Install the Gentic agent skill to teach your agent the optimal workflow so it gets the best results automatically.
npx skills add gentic-co/agent-skillsWorks with Claude Code, Cursor, Copilot, and 40+ other agents.
Pay per call, not per seat
A flat 5¢ every time your agent reads reviews. No monthly platform fee, no per-review charge.
| Tool | Cost |
|---|---|
| junip_get_reviews | 5¢ / call |
Pricing is pulled live from the Gentic MCP manifest so it always matches what you'll actually be charged.
Why agent-native reviews?
Review dashboards were built for a human scrolling a feed. This one was built for an agent that needs to read, filter, and act on reviews programmatically.
No UI to learn
Your AI agent is the interface. Ask for the reviews you need in natural language — no exports, no CSV downloads, no dashboard tour.
Composable workflows
Chain review reads with sentiment analysis, support triage, ad-copy generation, or your data warehouse. Build end-to-end review pipelines your way.
Portable
Works with any MCP-compatible client — Claude Web, Claude Code, OpenClaw, ChatGPT, n8n, and more. Switch clients without changing a thing.
Pay per use
No monthly seats or platform fees. You pay a flat 5¢ per call — only when your agent actually reads reviews.