Copy Markdown is an MCP server published by io.github.michaelvereb, hosted at www.copymarkdown.md. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 4 tools, including url_to_markdown, generate_content_md, generate_design_md, generate_links_md.
Extract clean markdown, DESIGN.md specs, and link graphs from any URL for LLMs.
12 connections through 5 shared values. Tap any node.
Extract clean, token-efficient Markdown from any public URL with headings, tables, code blocks, and links intact.
| Parameter | Type | Description |
|---|---|---|
| url * | string | Full URL to scrape (e.g. https://docs.example.com/guide) |
| api_key | string | Optional: your copymarkdown.md API key for higher rate limits |
{
"name": "url_to_markdown",
"title": "Extract Markdown from URL",
"description": "Extract clean, token-efficient Markdown from any public URL with headings, tables, code blocks, and links intact.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Full URL to scrape (e.g. https://docs.example.com/guide)"
},
"api_key": {
"type": "string",
"description": "Optional: your copymarkdown.md API key for higher rate limits"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Extract the core article or documentation body from any URL into a standardized CONTENT.md format, stripping headers, footers, and advertising noise.
| Parameter | Type | Description |
|---|---|---|
| url * | string | Full URL to extract content from |
| api_key | string | Optional: your copymarkdown.md API key for higher rate limits |
{
"name": "generate_content_md",
"title": "Generate Content Markdown",
"description": "Extract the core article or documentation body from any URL into a standardized CONTENT.md format, stripping headers, footers, and advertising noise.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Full URL to extract content from"
},
"api_key": {
"type": "string",
"description": "Optional: your copymarkdown.md API key for higher rate limits"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Extract a standardized DESIGN.md from any URL — CSS custom properties, typography hierarchy, button/card specifications, color palettes, and AI layout guidelines.
| Parameter | Type | Description |
|---|---|---|
| url * | string | URL to generate a DESIGN.md for |
| api_key | string | Optional: your copymarkdown.md API key for higher rate limits |
{
"name": "generate_design_md",
"title": "Generate Design Markdown",
"description": "Extract a standardized DESIGN.md from any URL — CSS custom properties, typography hierarchy, button/card specifications, color palettes, and AI layout guidelines.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "URL to generate a DESIGN.md for"
},
"api_key": {
"type": "string",
"description": "Optional: your copymarkdown.md API key for higher rate limits"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Extract a complete link graph into a standardized LINKS.md format from any URL, separating internal routes from outbound citations and references with anchor text.
| Parameter | Type | Description |
|---|---|---|
| url * | string | URL to extract link graph from |
| api_key | string | Optional: your copymarkdown.md API key for higher rate limits |
{
"name": "generate_links_md",
"title": "Generate Links Markdown",
"description": "Extract a complete link graph into a standardized LINKS.md format from any URL, separating internal routes from outbound citations and references with anchor text.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "URL to extract link graph from"
},
"api_key": {
"type": "string",
"description": "Optional: your copymarkdown.md API key for higher rate limits"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.