Bienvenido al servidor de Protocolo de contexto de modelo (MCP) para pure.md .
pure.md permite que tus scripts, API, apps, agentes, etc., accedan de forma fiable a contenido web en formato Markdown. Simplemente añade el prefijo pure.md/ a cualquier URL. Evita la detección de bots, renderiza JavaScript para SPA y puede convertir HTML, PDF, imágenes y más a Markdown puro. Como una CDN para contenido Markdown, almacena en caché global las respuestas para futuras solicitudes al mismo recurso, lo que reduce la carga de los servidores web de origen.
Sin puremd-mcp, los agentes locales pueden no poder obtener contenido web. puremd-mcp enseña a los clientes MCP como Cursor, Windsurf y Claude Desktop cómo adoptar la funcionalidad de pure.md, brindándoles capacidades de búsqueda y desbloqueo web.
puremd-mcp viene con dos herramientas:
unblock-url - Extrae Markdown de páginas web sin bloquearse
search-web - Busca en la web una consulta y concatena los resultados en Markdown
El Protocolo de Contexto de Modelo (MCP) , desarrollado por Anthropic, es un estándar abierto que permite a los sistemas de IA interactuar fluidamente con un ecosistema de herramientas. Con él, clientes MCP como Cursor, Windsurf y Claude Desktop pueden aprender a usar diversas API y otras funcionalidades.
Generar una clave API es un paso opcional que desbloquea límites de velocidad más altos. Si desea usar el servidor MCP pure.md de forma anónima, simplemente configure el valor PUREMD_API_KEY como una cadena vacía ( "" ).
Regístrese para obtener una nueva cuenta en pure.md : ¡registrarse es gratis!
En el panel de control, genere un nuevo token de API
Copie el token y úselo para el valor PUREMD_API_KEY en el archivo de configuración de su cliente MCP (ver a continuación)
Related MCP server: mult-fetch-mcp-server
Agregue lo siguiente a su archivo ~/.cursor/mcp.json :
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}Agregue lo siguiente a su archivo ./codeium/windsurf/model_config.json :
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}Agregue lo siguiente a su archivo ~/Library/Application\ Support/Claude/claude_desktop_config.json :
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}Para instalar puremd-mcp para Claude Desktop automáticamente a través de Smithery :
npx -y @smithery/cli install @puremd/puremd-mcp --client claude| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search-webunblock-urlScored across 2 tools
The two tools have clearly distinct purposes: 'search-web' appears to perform web searches, while 'unblock-url' likely handles URL unblocking or access. There is no overlap in functionality, making them easily distinguishable.
Both tools follow a consistent verb-noun pattern with hyphen separation (e.g., 'search-web', 'unblock-url'), and they use clear, action-oriented verbs. There are no deviations in naming style.
With only 2 tools, the server feels thin and likely incomplete for a web-related domain. This minimal set suggests significant gaps in coverage, such as missing operations for browsing, filtering, or managing search results.
Inferred as a web search/access server, the toolset is severely incomplete. It lacks core operations like retrieving search results, handling pagination, or managing blocked URLs beyond unblocking. This will likely cause agent failures in typical workflows.
Turn any public website into an MCP server for agents to search, read and navigate.
MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
