Skip to main content
Glama
Sign In
Semantic DOM Filter MCP Server

Semantic DOM Filter MCP Server

by krishankb-de
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Semantic DOM Filter MCP Server

A high-pass filter that sits between chaotic web pages and clean LLM context windows. Converts ~100KB HTML into ~2KB Semantic Markdown with integer IDs, eliminating selector hallucination and dramatically reducing token usage.

Architecture

User Prompt → LLM Agent → Semantic MCP Server
                               ↓
                    ┌──────────────────────┐
                    │  Playwright (Chromium)│
                    │         ↓            │
                    │  Accessibility Tree   │
                    │         ↓            │
                    │  Semantic Processor   │
                    │  ├─ Visibility Filter │
                    │  ├─ Struct. Flatten   │
                    │  └─ Intent Pruning    │
                    │         ↓            │
                    │  Markdown Synthesizer │
                    └──────────────────────┘
                               ↓
              Clean Semantic Map → LLM Agent
                               ↓
              Action (click id=7) → Semantic Diff

Related MCP server: HTML to Markdown Converter MCP

Tools

get_semantic_view

Navigate to a URL and get a filtered semantic map.

Parameter

Type

Description

url

string

URL to navigate to

task_intent

string

What you're trying to do (guides filtering)

Intent-guided filtering:

  • "read content" / "find pricing" → prunes navigation, footers

  • "fill form" / "login" → focuses on inputs, buttons

  • "find X" / "navigate" → keeps navigation, prunes long text

perform_action

Execute an action and get back only what changed (semantic diff).

Parameter

Type

Description

action

enum

click, type, select, hover, scroll, wait, press_key, go_back, go_forward, navigate

id

number?

Semantic ID of the target element

value

string?

Text to type, option to select, scroll direction, key to press

url

string?

URL for navigate action

get_current_state

Re-extract the semantic map without navigating. Useful to refresh after multiple actions.

Parameter

Type

Description

task_intent

string?

Optionally change the intent filter

get_screenshot

Capture a PNG screenshot of the current viewport.

Parameter

Type

Description

full_page

boolean?

Capture the full scrollable page

Output Format

# Example Page
**URL:** https://example.com
**Task:** find the pricing table
**Stats:** 23 semantic nodes (filtered from 847 raw nodes)

## Page Structure
- **main**: "Main Content" (312 nodes)
- **navigation**: "Primary Nav" (45 nodes)

## Semantic Map

[Heading(1): "Pricing Plans", id=1]
[Text: "Choose the plan that works for you"]
[Button: "Monthly", id=3, selected]
[Button: "Annual", id=4]
[Heading(2): "Starter", id=5]
[Text: "$9/month"]
[Button: "Get Started", id=7]
[Heading(2): "Pro", id=8]
[Text: "$29/month"]
[Button: "Get Started", id=10]

Semantic Diff (after actions)

Instead of re-sending the whole page:

**Action:** click on id=3
**Result:** Changes detected

## Changes
Modified:
  [Button, id=3]: state.pressed: "unset" → "true"
Added: [Text: "Billed monthly"]
Removed: [Text: "Billed annually"]

Setup

npm install
npm run build

Usage with Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "semantic-dom": {
      "command": "node",
      "args": ["path/to/browser_mcp/dist/index.js"]
    }
  }
}

Usage with VS Code (Copilot)

Add to your .vscode/mcp.json:

{
  "servers": {
    "semantic-dom": {
      "type": "stdio",
      "command": "node",
      "args": ["${workspaceFolder}/dist/index.js"]
    }
  }
}

Why This Wins

Metric

Raw HTML

This MCP

Payload

~100KB

~2KB

Token cost

~25K tokens

~500 tokens

Selector accuracy

Hallucinated CSS

Integer IDs

After-action update

Full re-send

Diff only

Intent awareness

None

Prunes by task

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    This server cannot be deployed

    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Resources

    Related MCP Connectors

    Related MCP Servers

    • readdown-mcp

      zcag
      A
      license
      A
      quality
      D
      maintenance
      Converts web pages and HTML strings into clean, LLM-optimized Markdown with metadata extraction and token estimation. It uses a lightweight, browserless approach to provide token-efficient output for more effective LLM processing.
      2
      MIT

    • Browser MCP

      drisplabs
      A
      license
      A
      quality
      B
      maintenance
      Gives AI agents a compact, semantic interface to the browser, returning structured page snapshots with stable element IDs instead of raw DOM. Enables agents to navigate, interact, and extract information from web pages efficiently.
      26
      16 npm
      19
      MIT
    • PageMap

      PageMapofficial

      Retio-ai
      A
      license
      A
      quality
      C
      maintenance
      Converts raw HTML into structured, AI-readable page maps with 97% token reduction, enabling agents to read, click, type, and navigate any web page.
      13
      36
      AGPL 3.0