mcp-servers
Verified Safeby pulsemcp
Overview
An MCP server for fetching, cleaning, and intelligently extracting content from web pages, designed for agent-building frameworks.
Installation
npx -y @pulsemcp/pulse-fetchSecurity Notes
The server's runtime environment primarily uses Node.js `fetch` for network operations and sandboxed file system operations (in the OS temp directory or user-defined path) for caching. Build and test scripts utilize `child_process` functions, but these are not exposed during server runtime. Input validation with Zod schemas is applied to tool arguments. Authentication health checks are implemented to verify external API keys at startup. The primary security consideration for a web scraping tool is the trustworthiness of the URLs it is directed to, which is a client-side responsibility.
Similar Servers
klavis
Creates an AI agent that uses Klavis Strata to interact with Gmail and YouTube through MCP, demonstrating how to summarize a YouTube video and email the summary.
awesome-mcp-devtools
This repository provides a curated list of developer tools, SDKs, frameworks, libraries, utilities, and resources for working with Model Context Protocol (MCP) servers.
mcp
A collection of Model Context Protocol (MCP) servers designed to connect IBM products and other services to AI agents for enhanced capabilities across automation, data, development, infrastructure, observability, networking, research, and security.
tmcp
Build Model Context Protocol (MCP) servers for AI agents, providing schema-agnostic tools, resources, and prompts, with optional OAuth 2.1 authentication and distributed session management.