# The best MCP server for AI search. The answers buyers see, in your coding agent.

> Add one server to Claude Code, Cursor or Codex. Your agent asks twelve AI engines your buyers' questions, reads every answer and checks Google rankings, on your Honeyb key at the API's prices.

HTML page: https://www.honeyb.ai/platform/api/mcp

## MCP setup

The same key runs the MCP server at `https://platform.honeyb.ai/mcp` (Streamable HTTP), on the same credits and prices. Every config reads the key from an environment variable, so it never lands in a file, a commit or the chat.

Claude Code:

```bash
claude mcp add --transport http honeyb https://platform.honeyb.ai/mcp --scope project --header 'Authorization: Bearer ${HONEYB_API_KEY}'
```

Cursor, in `.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "honeyb": {
      "url": "https://platform.honeyb.ai/mcp",
      "headers": { "Authorization": "Bearer ${env:HONEYB_API_KEY}" }
    }
  }
}
```

Codex, in `~/.codex/config.toml`:

```toml
[mcp_servers.honeyb]
url = "https://platform.honeyb.ai/mcp"
bearer_token_env_var = "HONEYB_API_KEY"
```

## Eight tools. Two spend credits.

Your agent quotes the price before it spends anything, then asks, polls and reads. Every tool runs the same operation as the REST API.

| Tool | What it does | Spends credits |
| --- | --- | --- |
| `list_engines_and_prices` | Lists the engines a task can run on, whether each searches the web, and every operation with its price and limits. | No |
| `create_visibility_task` | Asks the engines you pick a set of prompts about a brand and reads every answer: whether the brand is named, the competitors beside it, the sentiment and the pages cited. | Yes |
| `get_task` | Returns a task's status, its answer counts and the credits held and charged. The agent polls it until the task finishes. | No |
| `get_task_results` | Returns every answer, one row per prompt and engine: the answer text, the brand and competitor mentions and the sentiment. | No |
| `get_task_citations` | Returns every page the engines cited, with its domain, page classification, position and whether the citing answer named the brand. | No |
| `create_rank_check` | Checks where a domain ranks on Google for up to 1,000 keywords: position, ranking URL, SERP features and the AI Overview citation. | Yes |
| `get_rank_check` | Returns a rank check's status and keyword counts, and collects the keywords Google has finished. The agent polls it about once a minute. | No |
| `get_rank_check_results` | Returns one row per keyword: position, ranking URL and title, SERP features and whether the AI Overview cited the domain. | No |

## Server

| Item | Detail |
| --- | --- |
| Server | https://platform.honeyb.ai/mcp |
| Transport | Streamable HTTP, stateless, one JSON-RPC message per request |
| Sign-in | A Honeyb API key as a bearer token in the Authorization header; a request without one gets a 401 |
| Tools | 8: create_visibility_task and create_rank_check spend credits, the rest are free |
| Task size | Up to 300 prompts a task and 1,000 keywords a rank check |
| Location | AI answers: run each prompt from any country, and ChatGPT prompts from a US state too. Google rank checks: any Google location code, from a country down to a city. |
| Rate limit | Tool calls spend the key's 3,000 requests an hour, shared with the REST API; connecting and listing tools spend a separate allowance |
| Results kept | 30 days after submission; the task record and charge stay |
| Failed work | Never charged: failed answers and unmeasured keywords are free |

## Setup prompt

Paste this into Claude Code, Cursor or Codex. It carries no key.

```text
Set up the Honeyb API in this project and run a first task.

My Honeyb API key is in the HONEYB_API_KEY environment variable. Read it from there every time. Never write the key into a file, a commit or this chat.

1. Add the Honeyb MCP server at https://platform.honeyb.ai/mcp (streamable HTTP) with the header "Authorization: Bearer" followed by the value of HONEYB_API_KEY.
   - Claude Code: add a "honeyb" server to .mcp.json with "type": "http", "url": "https://platform.honeyb.ai/mcp" and "headers": { "Authorization": "Bearer ${HONEYB_API_KEY}" }
   - Cursor: add a "honeyb" server to .cursor/mcp.json with "url": "https://platform.honeyb.ai/mcp" and "headers": { "Authorization": "Bearer ${env:HONEYB_API_KEY}" }
   - Codex: add [mcp_servers.honeyb] to ~/.codex/config.toml with url = "https://platform.honeyb.ai/mcp" and bearer_token_env_var = "HONEYB_API_KEY"
2. Call list_engines_and_prices and show me the engines.
3. Ask me for my brand name, my website and one question my buyers ask AI. Ask me to confirm, because it spends credits, then call create_visibility_task with that brand, that question as the prompt, and the engines chatgpt, google_ai_overviews and google_ai_mode.
4. Poll get_task until the status is completed or failed.
5. Call get_task_results and get_task_citations, then tell me which brands each engine named and which sources it cited.
```

## What the API returns

Every path is on `https://app.honeyb.ai` and takes your key as a bearer token.

| Method | Path | What it does |
| --- | --- | --- |
| POST | `/api/platform/v1/tasks` | Submit a brand, up to 300 prompts and the engines to ask. |
| GET | `/api/platform/v1/tasks/{id}` | Task status, answers expected, completed and failed, and the settled cost. |
| GET | `/api/platform/v1/tasks/{id}/results` | One row per answer. |
| GET | `/api/platform/v1/tasks/{id}/citations` | One row per cited page. |
| POST | `/api/platform/v1/rank/check` | A domain and up to 1,000 keywords, checked on Google. |
| GET | `/api/platform/v1/rank/check/{id}` | Rank check status and keyword counts. |
| GET | `/api/platform/v1/rank/check/{id}/results` | One row per keyword. |

### Raw AI answers

- The answer text
- The cited sources
- Collection metadata: engine, country and time

| Field | What it holds |
| --- | --- |
| `prompt` | The question, exactly as it was asked. |
| `engine` | Which engine answered, as a stable slug: chatgpt, google_ai_overviews, google_ai_mode and the rest. |
| `answer` | The full answer text the app showed. |
| `createdAt` | When the answer was captured. |
| `url`, `domain`, `position` | Every source the answer cited, in the order it cited them, from the citations endpoint. |

### Enriched AI answers

- Everything in a raw answer
- Brands detected
- Competitors
- Sentiment
- Classified citations

| Field | What it holds |
| --- | --- |
| `brandMentions` | How many times the answer named your brand. |
| `competitorsMentioned` | Every other brand the answer named beside yours. |
| `sentiment` | The tone toward your brand: positive, neutral or negative. |
| `sentimentConfidence` | How sure that reading is, from 0 to 100. |
| `pageClassification` | What kind of page each source is: listicle, comparison, how-to, article, product page, category page, homepage or other. |

## Engines

Every engine is captured in a real browser session on the product people use, with memory and personalization off. Pass the slug in a task's `engines` list.

| Engine | Slug | Capture | Location |
| --- | --- | --- | --- |
| ChatGPT | `chatgpt` | Real browser session | Any country or US state |
| Google AI Overviews | `google_ai_overviews` | Real browser session | Any country |
| Google AI Mode | `google_ai_mode` | Real browser session | Any country |
| Gemini | `gemini` | Real browser session | Any country |
| Bing Copilot | `copilot` | Real browser session | Any country |
| Naver AI Briefing | `naver_ai_briefing` | Real browser session | Any country |
| Naver AI Mode | `naver_ai_mode` | Real browser session | Any country |
| ERNIE | `ernie` | Real browser session | Any country |
| Perplexity | `perplexity` | Real browser session | Any country |
| Claude | `claude` | Real browser session | Any country |
| Grok | `grok` | Real browser session | Any country |
| DeepSeek | `deepseek` | Real browser session | Any country |

## Prices per 1,000

US dollars per 1,000 delivered answers, from prepaid credits. No plan or subscription.

| Engine | Raw answers | Enriched answers |
| --- | --- | --- |
| ChatGPT | $1.05 | $2.05 |
| Google AI Overviews | $1.05 | $2.05 |
| Google AI Mode | $1.05 | $2.05 |
| Gemini | $1.05 | $2.05 |
| Bing Copilot | $1.05 | $2.05 |
| Naver AI Briefing | $1.05 | $2.05 |
| Naver AI Mode | $1.05 | $2.05 |
| ERNIE | $1.05 | $2.05 |
| Perplexity | $3.15 | $4.15 |
| Claude | $5.20 | $6.20 |
| Grok | $5.20 | $6.20 |
| DeepSeek | $5.20 | $6.20 |

Google rank checks: $1.00 per 1,000 checks. One check covers the top 10 results; a depth of 100 counts as ten checks.

One billable answer is one prompt on one engine, delivered. A failed capture is free, the price is held when you submit and settled to what arrived, and prepaid credits do not expire.

Tool calls spend the same prepaid credits as the REST API. Credits never expire, and a failed answer is never charged.

## Quickstart

Submit a task, poll it until its status is `completed` or `failed`, then read the answers. The key is read from the `HONEYB_API_KEY` environment variable.

```bash
curl -X POST https://app.honeyb.ai/api/platform/v1/tasks \
  -H "Authorization: Bearer $HONEYB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "brand": { "name": "Acme Billing", "url": "https://acmebilling.com" },
    "engines": ["chatgpt", "google_ai_overviews", "perplexity"],
    "prompts": ["What is the best billing platform for SaaS?"]
  }'

# Poll until "status" is "completed" or "failed", then read the answers
curl https://app.honeyb.ai/api/platform/v1/tasks/TASK_ID/results \
  -H "Authorization: Bearer $HONEYB_API_KEY"
```

A real response: the ChatGPT answer to "best CRM for small businesses", captured in a real browser session in the United States, as `GET /tasks/{id}/results` and `/citations` return it, raw and shortened.

```json
{
  "prompt": "best CRM for small businesses",
  "engine": "chatgpt",
  "answer": "After researching the leading ...",
  "citations": [
    { "position": 1, "domain": "spotsaas.com" },
    { "position": 2, "domain": "stacknpilot.com" },
    { "position": 3, "domain": "itechguides.com" }
  ]
}
```

## FAQ

### What is the Honeyb MCP server?

A remote MCP server that turns the Honeyb API into tools, so an AI agent such as Claude Code, Cursor or Codex can ask ChatGPT and Google's AI your buyers' questions, read the brands and sources in each answer, and check Google rankings, on your Honeyb key.

### Which clients work with it?

Claude Code, Cursor and Codex with the config on this page, and any other MCP client that speaks Streamable HTTP and sends an Authorization header, such as VS Code. The server is at https://platform.honeyb.ai/mcp.

### Do I need an API key?

Yes. Every request carries your Honeyb API key as a bearer token, and the server answers 401 without one. Keep it in the HONEYB_API_KEY environment variable: every config here reads it from there, so it never lands in a file or a commit. Get your API key with the form on this page and we issue it within one working day.

### What does it cost?

The same as the REST API, from the same credits: AI answers from $1.05 per 1,000 raw and from $2.05 per 1,000 enriched, Google rank checks $1.00 per 1,000 checks. Listing, polling and reading are free.

### Will my agent spend credits without asking?

Only create_visibility_task and create_rank_check spend credits. The server tells the agent to confirm the price with you before a large task, and list_engines_and_prices gives it the figures to quote.

### What does the setup prompt do?

Paste it into Claude Code, Cursor or Codex. It tells the agent to add the server with the key read from HONEYB_API_KEY, list the engines, ask you for a brand and one buyer question, and run a first task on ChatGPT, Google AI Overviews and Google AI Mode.

## Get an API key

[Get your API key](https://www.honeyb.ai/platform/api/mcp) with the form on the page. We issue keys within one working day. Tell us your engines and volume.

## Every API page as Markdown

- [Honeyb API](https://www.honeyb.ai/platform/api.md): The AI search API: the answers AI engines show people, captured in real browser sessions, read into brands and sources, with Google rank checks on the same key.
- [API Pricing](https://www.honeyb.ai/platform/api/pricing.md): Every engine's price per 1,000 answers, raw and enriched, and the price of Google rank checks. Prepaid credits, no subscription.
- [LLM Scraper API](https://www.honeyb.ai/platform/api/llm-scraper-api.md): Ask every AI engine the same prompt and get each answer with every source it cited, in one call.
- [ChatGPT Scraper API](https://www.honeyb.ai/platform/api/chatgpt-scraper-api.md): The answer the ChatGPT app gives, with every source it cited, as JSON.
- [AI Overviews API](https://www.honeyb.ai/platform/api/ai-overviews-api.md): The AI Overview Google shows above the results, with every page it cited, as JSON.
- [Google AI Mode API](https://www.honeyb.ai/platform/api/ai-mode-api.md): The answer Google AI Mode gives, with every source it cited in order, as JSON.
- [Perplexity API](https://www.honeyb.ai/platform/api/perplexity-api.md): The answer Perplexity gives real people, with every source it cited, captured in a real browser session, as JSON.
- [AI Visibility API](https://www.honeyb.ai/platform/api/ai-visibility-api.md): Every AI answer read for you: the brands named, the competitors beside yours, the sentiment and every source classified.
- [AI Mentions API](https://www.honeyb.ai/platform/api/ai-mentions-api.md): Every AI answer that named a brand, with the engine, the prompt, the sentiment, the competitors and the sources.
- [Rank Tracking API](https://www.honeyb.ai/platform/api/rank-tracking-api.md): Google position, ranking URL and whether the AI Overview cites you, per keyword, on the same key as the AI answers.
- [ChatGPT app vs its API](https://www.honeyb.ai/platform/api/chatgpt-app-vs-api.md): The same buying questions put to the ChatGPT app and its API cite different sources, measured side by side.
- [Backlinks API](https://www.honeyb.ai/platform/api/backlinks-api.md): Referring domains, backlinks, anchors and new or lost links for any domain or URL. Early access.
- [Keyword Data API](https://www.honeyb.ai/platform/api/keyword-data-api.md): Search volume, CPC, difficulty, keyword ideas and Google Trends for any market, plus AI prompt volume. Early access.
- [SERP API](https://www.honeyb.ai/platform/api/serp-api.md): Where a domain ranks on Google for any keyword, the URL and title shown, every SERP feature and whether the AI Overview cites it, any country down to a city.
