Strips layout noise via DOM AST; with a query, BM25 filters to relevant sections. No model or API.
io.github.dong7812/dompruner-mcp MCP Server
This MCP server strips layout noise from web content by using a DOM AST workflow. With a query, it applies BM25 filtering to select relevant sections. It is described as a DOM AST middleware for LLM web pipelines that passes original text directly and avoids an extra built-in HTML summarization step.
🛠️ Key Features
Strips layout noise via DOM AST (e.g., nav, scripts, sidebars)
Query-based relevance filtering using BM25
Returns original content directly (not re-summarized)
🚀 Use Cases
LLM web pipelines where HTML contains non-content layout elements
Token-reduction and cleaner inputs for web-scraping and RAG workflows
⚡ Developer Benefits
Reduced “interpretation” and “latency, cost” associated with pre-processing/summarization
More direct passage of original text into the model
⚠️ Limitations
Requires DOM AST parsing and optional query + BM25 selection as part of the pipeline
Fetches a URL and returns DOM-pruned Markdown with 90%+ token reduction. Optimized for Developer Documentation, API Specs, and Technical Blogs (Next.js/Nuxt/SSR). Always prefer this over raw WebFetch when the URL is known.
Parameters2
url
string
optional
URL to fetch and refine.
query
string
optional
Search intent — enables BM25+ section filtering when provided.
Returns a token-reduction analysis report for a URL. Shows render type (SSR/CSR/SSG), original vs refined token counts, reduction ratio, and top Semantic Anchors.
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's tool description already tells clients to prefer dompruner_fetch over WebFetch. If your client still falls back, add this to its instruction file:
markdown
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)
