What content types does it support?
It can summarize plain text, web pages (via URL), PDF documents, EPUB books, and HTML content. You specify the `type` parameter when using the `summarize` tool.
@0xshellming
Basic information
MCP Server for AI Summarization
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"content-summarizer": {
"command": "node",
"args": [
"{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Mcp Summarizer Server is a Model Context Protocol (MCP) server that provides intelligent summarization of various content types using Google’s Gemini 1.5 Pro model. It is powered by 3MinTop, an AI reading tool designed to transform complex content into clear, concise summaries. This server is for developers and users who need automated content summarization within MCP-compatible applications.
Install dependencies with pnpm install, build with pnpm run build, and start with pnpm start. For desktop app integration, add the server configuration to your app’s MCP settings, specifying the absolute path to the compiled dist/index.js file.
It can summarize plain text, web pages (via URL), PDF documents, EPUB books, and HTML content. You specify the `type` parameter when using the `summarize` tool.
It requires Node.js and pnpm. Build and start commands are `pnpm build` and `pnpm start`. No external database or network service (beyond the summarization API itself) is mentioned in the README.
The README states that the service is “powered by 3MinTop” but does not disclose pricing or API key requirements. No authentication parameters are listed in the tool’s schema; the server handles communication with the Gemini model through the 3MinTop infrastructure.
Yes. The `style` parameter accepts `concise`, `detailed`, or `bullet-points` to tailor the output. You can also set a `focus` aspect to emphasize specific parts of the content.
Add a JSON entry to your app’s `mcpServers` configuration with command `node` and args pointing to the absolute path of the built `dist/index.js` file. Example is provided in the README.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
Hindsight: Agent Memory That Learns
Mandate Law is a law firm for AI products, agents, and the consumer apps they live in, built so coding agents can work with counsel directly. An agent can check whether a request is in scope and get the fixed fee (free a
Comments