# recomention

> recomention is a freemium MCP server for marketing and seo. Ask whether AI engines recommend your product and read the full visibility report. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, CLI, Web
- **Website:** https://www.recomention.com/developers
- **Repository:** https://github.com/recomention/mcp
- **MCP Registry name:** io.github.recomention/mcp
- **Categories:** marketing and SEO, analytics and data
- **Listing updated:** 2026-11-14

## About

This server lets a coding agent answer a question like whether ChatGPT recommends a product for a given category. It wraps the recomention JSON API: an agent can browse public AI rankings, get suggested buyer questions, start a report, poll until it finishes and read the result. A finished report gives each engine's count of answers that named the product, who was named instead, the sources the engines read and a fix list. Engines that could not run are listed as skipped rather than counted against you.

Two ways to connect exist. The npm package runs locally over stdio with an API key from the account's Developers page; public rankings and suggested questions work without one. The hosted endpoint signs in with OAuth and needs no key, with reading and paid starts approved separately and starts using report credits only.

Starting a report is never free: the request must name its funding, either an agency credit or your own provider keys on an Agent plan. Those keys are read from the server's environment, never from tool arguments. API limits are 60 requests per key per minute and 10 report starts per key per hour.

## Features

- **Public rankings:** Lists AI rankings and shows each ranked product as named in n of m answers.
- **Suggested questions:** Generates buyer questions from fixed templates without a model call.
- **Report start and status:** Starts a paid report and polls until it completes.
- **Detailed results:** Returns per-engine scores, competitors named, sources and a fix list.
- **Bring your own keys:** Runs reports on your OpenAI, Anthropic, Gemini and other keys on an Agent plan.
- **Hosted OAuth option:** Connect Claude or ChatGPT with sign-in instead of an API key.

## Good for

- Check whether AI engines recommend a product for a buyer question
- See which competitors are named instead
- Draft buyer questions to test a category
- Read the sources that engines cited
- Generate a fix list for improving AI visibility

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http mcp https://mcp.recomention.com/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.recomention.com/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.recomention.com/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.recomention.com/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.recomention.com/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.recomention.com/mcp"
    }
  }
}
```

## Tools

- `recomention_rankings_list`: Lists the public AI rankings; no key needed.
- `recomention_rankings_get`: Returns one ranking with the questions and products named.
- `recomention_suggest_prompts`: Suggests buyer questions from fixed templates for a domain and category.
- `recomention_report_start`: Starts a report funded by credits or your own provider keys.

## FAQ

### Do I need an API key?

Only for reports. Public rankings and suggested questions work without one; the hosted server uses OAuth instead.

### What does starting a report cost?

It spends one agency credit for a Full report, or runs on your own provider keys with an Agent plan; prices are not published.

### Are there rate limits?

The API allows 60 requests per key per minute and 10 report starts per key per hour.

### What does it need to run locally?

Node.js 20 or newer.

### Is recomention free?

recomention has a free plan, with paid plans for more usage or features.

### How do I add recomention to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.recomention.com/mcp

### What are the best alternatives to recomention?

The closest alternatives to recomention are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP, World Monitor and Calven.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [Calven](https://ai-powered.com/mcp/calven): Calven is an MCP server for marketing and seo.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [MCP](https://ai-powered.com/mcp/mcp-mwhffe53): MCP is a freemium MCP server for marketing and seo.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/recomention
