DOM AST middleware for LLM web pipelines — strips layout noise (nav, scripts, sidebars) and passes original text directly. Add a query to filter to relevant sections with BM25.

When an LLM uses the built-in WebFetch, a smaller model pre-processes the HTML and hands back a summarized result — adding latency, cost, and interpretation you didn't ask for. DomPruner skips that entirely: DOM AST parsing strips noise and passes the original content directly to the model.

Call	Behavior
`dompruner_fetch(url)`	Strips layout noise → returns full extracted content
`dompruner_fetch(url, query)`	Strips layout noise → BM25 filters to relevant sections (falls back to full content if no match)

> [DomPruner] docs.python.org
> | Raw HTML  | 44,316 tokens |
> | DomPruner |  1,328 tokens |
> | Reduction |        97.0%  |
> Fetch: 194ms · Parse: 11.2ms

93.5% fewer context tokens than WebFetch on average. 45% faster end-to-end. → Full benchmark

Quick Start

No installation, no API key:

npx -y dompruner-mcp

Claude Code

{
  "mcpServers": {
    "dompruner": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "dompruner-mcp"]
    }
  }
}

Add to .mcp.json in your project root, or ~/.claude/.mcp.json for global. Run /mcp to verify.

Claude Desktop

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

{
  "mcpServers": {
    "dompruner": {
      "command": "npx",
      "args": ["-y", "dompruner-mcp"]
    }
  }
}

Cursor / Windsurf / other MCP clients

{
  "mcpServers": {
    "dompruner": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "dompruner-mcp"]
    }
  }
}

Remote HTTP (no install, always up to date)

For clients that support HTTP transport — no Node.js install required, always runs the latest version:

{
  "mcpServers": {
    "dompruner": {
      "url": "https://dompruner-mcp.vercel.app/api/mcp"
    }
  }
}

LangChain / LangGraph

langchain-mcp-adapters wraps any MCP stdio server as LangChain tools automatically:

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
    "dompruner": {
        "command": "npx",
        "args": ["-y", "dompruner-mcp"],
        "transport": "stdio",
    }
})
tools = await client.get_tools()

Ensuring Your AI Always Uses DomPruner

DomPruner's tool description already tells clients to prefer dompruner_fetch over WebFetch. If your client still falls back, add this to its instruction file:

When retrieving a URL, always use dompruner_fetch instead of WebFetch.
- URL known → dompruner_fetch(url, query?)
- URL unknown → search for the URL first, then dompruner_fetch(url)

Client	Instruction file
Claude Code	`CLAUDE.md` (project) or `~/.claude/CLAUDE.md` (global)
Cursor	`.cursorrules`
Windsurf	`.windsurfrules`
Cline	`.clinerules`
GitHub Copilot	`.github/copilot-instructions.md`

Tools

Tool	Description
`dompruner_fetch`	Fetch a URL → DOM-refined Markdown. Optional `query` enables BM25+ section filtering.
`dompruner_sitemap`	Fetch all pages in a sitemap.xml → one refined Document per page.
`dompruner_analyze`	Token-reduction report for a URL without full content.

→ Full tool reference

Benchmark Summary

Metric	WebFetch	DomPruner
Avg context tokens	~15,735	~1,019 (93.5% less)
Answer quality (10 queries)	9 / 10	8 / 10
Avg response time	5,811 ms	3,168 ms (45% faster)
Content fidelity	Summarized by small model	Original text preserved
Extra API key / infra	No	No

→ Full benchmark · Architecture

dompruner-py — Python port. DomPrunerLoader, DomPrunerSitemapLoader, DomPrunerFetchTool for LangChain. pip install dompruner.
LangChain integrations — dompruner-py listed as a third-party web loader.