DomPruner MCP
An MCP server that strips layout noise and boilerplate from HTML via DOM AST extraction, reducing token usage by 97-99%. It supports fetching URLs with optional BM25 query filtering to extract relevant sections, fetching sitemaps, and analyzing token reduction reports without requiring an API key or vector database.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://dompruner-mcp.vercel.app/api/mcpWhat its tools do
2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Read-only (2)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Fetch a URL and return DOM-refined Markdown with optional BM25 section filtering
- Fetch all pages in a sitemap.xml to generate one refined Document per page
- Generate a token-reduction report for a URL without retrieving full content
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- dompruner 0.3.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 2 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {
"listChanged": true
}
}Tools
2 advertised
dompruner_fetch
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.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "URL to fetch and refine."
},
"query": {
"type": "string",
"description": "Search intent — enables BM25+ section filtering when provided."
}
},
"additionalProperties": false
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"markdown",
"stats"
],
"properties": {
"stats": {
"type": "object",
"required": [
"hostname",
"originalTokens",
"refinedTokens",
"savedTokens",
"reductionPercent",
"fetchMs",
"parseMs"
],
"properties": {
"fetchMs": {
"type": "number"
},
"parseMs": {
"type": "number"
},
"hostname": {
"type": "string"
},
"savedTokens": {
"type": "number"
},
"refinedTokens": {
"type": "number"
},
"originalTokens": {
"type": "number"
},
"reductionPercent": {
"type": "string"
}
},
"additionalProperties": false
},
"markdown": {
"type": "string",
"description": "DOM-pruned Markdown content."
}
},
"additionalProperties": false
}{
"title": "Fetch & Prune Web Page",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}dompruner_analyze
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.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "URL to analyze."
}
},
"additionalProperties": false
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url",
"renderType",
"originalTokens",
"refinedTokens",
"reductionPercent",
"fetchMs",
"parseMs",
"topAnchors"
],
"properties": {
"url": {
"type": "string"
},
"fetchMs": {
"type": "number"
},
"parseMs": {
"type": "number"
},
"renderType": {
"type": "string",
"description": "SSR, CSR, or SSG"
},
"topAnchors": {
"type": "array",
"items": {
"type": "string"
},
"description": "Top 5 semantic section headings."
},
"refinedTokens": {
"type": "number"
},
"originalTokens": {
"type": "number"
},
"reductionPercent": {
"type": "string"
}
},
"additionalProperties": false
}{
"title": "Analyze Token Reduction",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}Prompts
Not advertised
Resources
Not advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-06: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 565 ms
- 95th percentile latency
- 565 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 565 ms · metadata changed · 2 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http dompruner-mcp-vercel https://dompruner-mcp.vercel.app/api/mcpCodex
codex mcp add dompruner-mcp-vercel --url https://dompruner-mcp.vercel.app/api/mcpCursor
{
"mcpServers": {
"dompruner-mcp-vercel": {
"url": "https://dompruner-mcp.vercel.app/api/mcp"
}
}
}Cline
{
"mcpServers": {
"dompruner-mcp-vercel": {
"type": "streamableHttp",
"url": "https://dompruner-mcp.vercel.app/api/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"dompruner-mcp-vercel": {
"type": "http",
"url": "https://dompruner-mcp.vercel.app/api/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http dompruner-mcp-vercel https://dompruner-mcp.vercel.app/api/mcpClaude Desktop
https://dompruner-mcp.vercel.app/api/mcpWindsurf
{
"mcpServers": {
"dompruner-mcp-vercel": {
"serverUrl": "https://dompruner-mcp.vercel.app/api/mcp"
}
}
}Let your agent find its tools
Find servers like DomPruner MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.