Memex

Protocolo Memex para el contexto del modelo
Memex es una herramienta para Model Context Protocol (MCP) que le permite analizar contenido web y agregarlo a su base de conocimiento.
La herramienta se inspiró en el proyecto Memex de Vannevar Bush .
Requisitos
Necesitará claves API para los siguientes servicios:
La base de conocimientos producida por esta herramienta se almacena como archivos Markdown para que puedan verse con cualquier visor de Markdown, pero se recomienda Obsidian .
Related MCP server: Documentation Crawler & MCP Server
Instalación
pip install mcp-memexAgregue lo siguiente a su claude_desktop_config.json y reemplace los marcadores de posición con las rutas reales y las claves API:
{
"mcpServers": {
"memex": {
"command": "uv",
"args": [
"--directory",
"PATH_TO_LOCAL_MEMEX_REPO",
"run",
"mcp-memex",
"--index",
"PATH_TO_MEMEX_INDEX",
"--workspace",
"PATH_TO_OBSIDIAN_VAULT"
],
"env": {
"ANTHROPIC_API_KEY": "YOUR-API-KEY",
"FIRECRAWL_API_KEY": "YOUR-API-KEY",
"VOYAGE_API_KEY": "YOUR-API-KEY"
}
}
}
}Uso
Comience por hacerle una pregunta a Claude con una lista de URL a las que hacer referencia.
What is the capital of France? "https://en.wikipedia.org/wiki/France"Una vez que Claude haya terminado de analizar el contenido, verás los resultados en tu bóveda de Obsidian. Podrás hacer preguntas sobre el contenido y Memex usará la base de conocimientos para responderlas.
What is the capital of France?Desarrollo
Para ejecutar la herramienta localmente, puede utilizar el siguiente comando:
npx @modelcontextprotocol/inspector \
uv \
--directory PATH_TO_LOCAL_MEMEX_REPO \
run \
mcp-memex \
--index PATH_TO_MEMEX_INDEX \
--workspace PATH_TO_OBSIDIAN_VAULTLuego abra el inspector y conéctese al servidor.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that allows LLMs to interact with web content through standardized tools, currently supporting web scraping functionality.1MIT
- AlicenseNot gradedqualityDmaintenanceToolset that crawls websites, generates Markdown documentation, and makes that documentation searchable via a Model Context Protocol (MCP) server for integration with tools like Cursor.42MIT
- AlicenseNot gradedqualityBmaintenanceA self-hosted MCP server that reads web pages and converts them to Markdown, with built-in web search and anti-crawl fallback using Playwright.1MIT
- FlicenseBqualityDmaintenanceCompiles web sources into structured, backlinked wiki pages in an Obsidian-compatible vault and enables querying the knowledge base via MCP.3
Related MCP Connectors
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Web tools for agents: fetch URL as markdown (free MCP) + x402 scrape, links, AI JSON, snapshot.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/narphorium/mcp-memex'
If you have feedback or need assistance with the MCP directory API, please join our Discord server