# Blogs Segmentation MCP

**Count** blog posts by site, author, and more. One tool: `aggregate_webz_blogs`.

## MCP endpoint

```text
https://seg-blogs-mcp.webz.io/mcp
```

## How it works

Ask which blogs dominate a topic. The assistant calls `GET /seg_api/blogs`. The MCP adds `site_type:blogs` to `q` automatically.

## Connect your client

Replace `YOUR_WEBZ_TOKEN` with your token.

### Cursor

Add this to `~/.cursor/mcp.json` (`%USERPROFILE%\.cursor\mcp.json` on Windows) and restart Cursor:

```json
{
  "mcpServers": {
    "webz-seg-blogs": {
      "url": "https://seg-blogs-mcp.webz.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_WEBZ_TOKEN"
      }
    }
  }
}
```

Setup: `https://seg-blogs-mcp.webz.io/`.

### Claude Desktop

Merge the same `webz-seg-blogs` entry into your Claude Desktop config file - do not replace the whole file - then restart Claude Desktop:

| OS | Config file |
| --- | --- |
| macOS | `~/Library/Application Support/Claude/claude_desktop_config.json` |
| Linux | `~/.config/Claude/claude_desktop_config.json` |
| Windows | `%APPDATA%\Claude\claude_desktop_config.json` |

### Claude Code

Run in your project root:

```bash
claude mcp add --transport http webz-seg-blogs https://seg-blogs-mcp.webz.io/mcp --header "Authorization: Bearer YOUR_WEBZ_TOKEN"
```

### n8n

Add an **MCP Client Tool** node and connect it to an **AI Agent** node's **Tool** input:

| Field | Value |
| --- | --- |
| Endpoint | `https://seg-blogs-mcp.webz.io/mcp` |
| Server Transport | `HTTP Streamable` |
| Authentication | `Bearer Auth` |
| Tools to Include | `All` |

Create a **Bearer Auth** credential and paste your Webz.io API token as the bearer token. The agent receives a `aggregate_webz_blogs` tool.

### Claude.ai and ChatGPT (web)

Add `https://seg-blogs-mcp.webz.io/mcp` as a custom connector (Claude.ai: Settings > Connectors; ChatGPT: Settings > Apps & Connectors with Developer mode on). Both use OAuth: leave Client ID and Secret empty, then paste your Webz token on the authorize page. Setup instructions for every client are at [seg-blogs-mcp.webz.io](https://seg-blogs-mcp.webz.io/).

> [!NOTE]
> Opening the `/mcp` endpoint in a browser returns `401 Unauthorized` by design - browsers do not send your token. Use an MCP client.

## End-to-end example

### 1. What you ask

> Which blogs wrote the most about bitcoin in the last week?

### 2. What the assistant calls

Tool: `aggregate_webz_blogs`

| Argument | Value |
|----------|--------|
| `days` | `7` |
| `q` | `bitcoin` |
| `field` | `thread.site` (default with `organizations` if `field` is empty) |

### 3. What the MCP tool returns

```text
Query: bitcoin
Field: thread.site
Buckets: 100
- biltehqeeq.com: 493
- panahon.tv: 398
- anmaraviation.com.au: 315
- alfa-pages.co.uk: 280
- example-crypto-blog.net: 201
Next page: call again with from_offset=10
```

### 4. What you see from the assistant

> Over the last 7 days, Webz counted blog posts mentioning **bitcoin**. The busiest sites in the top bucket list include biltehqeeq.com (493 posts in this window), panahon.tv (398), and several others. These are **post counts per blog**, not article text. Say if you want the actual posts from one site; I can use the Blogs search MCP with `site:domain`.

## Tool parameters (simple view)

| Parameter | You usually say… | What the tool does |
|-----------|------------------|-------------------|
| `q` | topic, language | blogs boolean query |
| `field` | "by blog", "by author" | aggregation field |
| `days` | time window | lookback days |

Wait **1 second** between tool calls on this server.

## More detail

- [Segmentation API](news-blogs-forums-segmentation)
- [Blog filters](blogs-api-filters)