Dompruner MCP

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. Its README documents 3 tools, including dompruner_fetch, dompruner_sitemap, dompruner_analyze.

People who work with token reduction, web scraping and dom ast and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-29 · ★ 2 · #43 OF 93 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-18

MIT · TypeScript servers · how we verify → /methodology

01 · Install Dompruner MCP

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add dong7812-dompruner-mcp --transport http https://dompruner-mcp.vercel.app/api/mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "dong7812-dompruner-mcp": {
      "url": "https://dompruner-mcp.vercel.app/api/mcp"
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://dompruner-mcp.vercel.app/api/mcp

transport: streamable-http

endpoint alive - responded to MCP initialize · probed 2026-09-18

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · remote - your agent's requests go to dompruner-mcp.vercel.app

endpoint auth accepted our unauthenticated MCP initialize - no credentials needed to connect

repo age created 2026-08-06 - young repo, little track record yet

license MIT - declared in the repository

npm package dompruner-mcp - unscoped; check the name against the project README before installing

registry namespace io.github.dong7812 is GitHub-verified and matches the repo owner

03 · What Dompruner MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can fetch a URL → DOM-refined Markdown. Optional query enables BM25+ section filtering, and fetch all pages in a sitemap.xml → one refined Document per page.

The 3 tools it gives your agent

Extracted from the project's README - what dompruner-mcp lets an agent do.

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.

Latest releases

v0.5.1 · 2026-08-16

Fix · Clarified dompruner_fetch tool description to say "use your own native search tool" instead of "use web search." · The previous wording caused some MCP hosts (e.g. Glama) to interpret the phrase as a reference to…

v0.5.0 · 2026-08-16

What's new · dompruner_sitemap - full-site ingestion · Fetch every page in a sitemap.xml and return DOM-pruned Markdown for each, with 90%+ token reduction applied site-wide. · json · { "tool": "dompruner_sitemap"…

04 · Who maintains Dompruner MCP

dompruner-mcp is maintained by dong7812. It's the only MCP server we track from this author; the repo dates to Aug 2026.

05 · Facts

repository: github.com/dong7812/dompruner-mcp
website: https://github.com/dong7812/dompruner-mcp
category: web scraping - ranked #43 of 93 actively-maintained web scraping servers as of 2026-09-18.
release cadence: 2 releases in the last 90 days (latest 2026-08-16)
registry: io.github.dong7812/dompruner-mcp (active, first published 2026-08-19)
packages: npm:dompruner-mcp

06 · Dompruner MCP FAQ

Is Dompruner MCP still maintained?

Yes - as of 2026-09-18, its last commit was 2026-08-29 and it shipped 2 releases in the last 90 days. We re-verify nightly.

What can Dompruner MCP do?

With this server connected, an agent can fetch a URL → DOM-refined Markdown. Optional query enables BM25+ section filtering, and fetch all pages in a sitemap.xml → one refined Document per page.

How do I install Dompruner MCP?

Run `npx -y dompruner-mcp`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does Dompruner MCP require authentication?

No - the endpoint accepted our unauthenticated MCP initialize when probed on 2026-09-18; you can connect without credentials.

07 · Alternatives to Dompruner MCP

Alternatives to Dompruner MCP

Maintained web scraping servers if Dompruner MCP isn't the fit.

Pairs well with

Servers that cover what Dompruner MCP doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · En Convert · Fouradata MCP Server

More TypeScript MCP servers · Mindwtr · Keymem · Domain Search MCP · Hivelore · Megalinter · see all