Octen MCP Server

octen-mcp

MCP server for Octen Extract — turn any URL into clean, LLM-ready markdown. Plug into Claude / Cursor / VS Code / Windsurf and let the model pull the live web.

Why this MCP

Most extract tools (Firecrawl, Exa web_fetch, Tavily extract) hand you the page body. Octen gives you more, per page, in one call:

• highlights — pass a query and get the most relevant snippets ranked, not the whole page (cheaper context, better signal)
• category — topical classification {primary, secondary}
• page_structure — page typology {primary, secondary} (article / product / listing / index / …)

Quick start

You need an Octen API key — grab one at octen.ai.

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "octen": {
      "command": "npx",
      "args": ["-y", "octen-mcp"],
      "env": {
        "OCTEN_API_KEY": "your-key-here"
      }
    }
  }
}

Quit and reopen Claude Desktop. Ask "fetch octen.ai and summarize" — Claude routes to the extract tool automatically.

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "octen": {
      "command": "npx",
      "args": ["-y", "octen-mcp"],
      "env": { "OCTEN_API_KEY": "your-key-here" }
    }
  }
}

VS Code

The button prompts you for the API key on click — no manual editing needed. Or add to .vscode/mcp.json in your workspace:

{
  "servers": {
    "octen": {
      "command": "npx",
      "args": ["-y", "octen-mcp"],
      "env": { "OCTEN_API_KEY": "your-key-here" }
    }
  }
}

Claude Code (CLI)

One line, no JSON editing:

claude mcp add --scope user octen \
  -e OCTEN_API_KEY=your-key-here \
  -- npx -y octen-mcp

--scope user makes it available from any directory. Verify with claude mcp list — should show octen: ✓ Connected.

Windsurf / Cline / other MCP clients

Same npx -y octen-mcp command with OCTEN_API_KEY env — works in any MCP-compatible client.

Tool reference: extract

Full API reference: docs.octen.ai/api-reference/extract.

Example prompts to try

• Fetch octen.ai and summarize the main product features.
• Compare the positioning of firecrawl.dev and octen.ai.
• What does the Hacker News front page say right now? Pull the top 5 story titles.
• Search 'pricing' across firecrawl.dev — return only the relevant highlights. (triggers query → highlights)

How Octen handles edge cases

Real web pages fail in messy ways. Octen surfaces structured signals so your LLM agent can decide what to do, instead of guessing from an empty markdown blob.

The last row is the Octen-specific win: most extract tools would return status: success + a short body for that login wall and your agent has no signal it's garbage. Octen's page_structure classifier tells you upfront.

Environment variables

Local development

git clone https://github.com/Octen-Team/octen-mcp.git
cd octen-mcp
npm install
npm run build
OCTEN_API_KEY=<key> npm run inspect    # opens MCP Inspector

Tip — make Claude prefer this tool

If your client also has a built-in web-fetch tool, drop a hint in Claude Desktop's Customize / Project Instructions:

When the user asks to fetch or extract content from a URL, prefer the extract tool from the octen MCP server. Use query whenever the user is looking for something specific on the page (returns ranked highlights, not the whole body).

With the hint in place, a single tool call classifies three mixed URLs (article / homepage / discussion) in one shot:

License

MIT © Octen