"Marking Linux terminal commands as safe or unsafe for local execution" matching MCP servers:

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

Provides live wait times and office details for all 60 Oregon DMV field offices by scraping the ODOT website, with no authentication required.

MCP server that scrapes Terminal Trove to search CLI/TUI tools and retrieve design references like screenshots and install commands for agentic UI research.

Enables browser automation for LLMs on Linux display servers, supporting web interaction, screenshots, and JavaScript execution in a real browser.

Ultimate Standalone Terminal Browser & Web Scraper - Browse any website, extract content & links directly in your terminal.

A content fetcher that sanitizes, size-caps, and caches fetched content, protecting against injection attacks via the Model Context Protocol.

Enables coding agents to scan a public URL in passive or authorized mode and receive only bounded, sanitized structured findings (severity, confidence, standard, evidence, remediation) with quarantined evidence instead of raw page dumps. A second tool lets agents inspect the scanner's safety boundaries and coverage without making any network request.

Fetches web pages and converts them to clean, readable markdown format by extracting main content while removing navigation, ads, and other non-essential elements to minimize token usage.

Enables read-only retrieval of public web pages through MCP, with SSRF protection, no cookies or login state, and specialized anonymous parsing for Xiaohongshu, plus an opt-in Jina Reader fallback.

Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures.

Enables local web crawling and scraping through MCP, providing tools to fetch pages as Markdown, extract structured data with CSS selectors, and capture full-page screenshots while managing a shared browser instance.

Gives Claude control of a real, headed Chromium browser via Playwright, enabling web navigation, clicking, typing, screenshots, and JavaScript evaluation.

A headless, agent-controllable real browser as an MCP server that enables AI agents to navigate, click, fill, eval JavaScript, and take screenshots on localhost and allowed hosts, with no GUI required.

Automatically crawls documentation websites, converts them to organized markdown files, and generates condensed cheat sheets. Intelligently categorizes content into tools/APIs and provides local-first access to downloaded documentation.

Local-first realtime web research MCP for LM Studio with keyless SearXNG, clickable citations, adaptive deep research, provider health, and one-click Windows startup.

Enables agents to fetch web pages as Markdown from a self-hosted extraction service over stdio MCP, including single-page and bounded two-URL batch retrieval. It applies token limits, concurrency control, timeouts, optional API-key auth, and rejects obvious local or private targets.

Enables normal ChatGPT conversations and other MCP clients to search, open, and read public Xiaohongshu pages, search results, and notes through a user's manually logged-in local browser. It is read-only, local-first, and uses browser-visible DOM/meta without reading cookies or private-message bodies.

Lightweight MCP server for controlling a Windows Chrome instance from WSL, designed for AI coding agents with minimal token overhead and human-in-the-loop support.

Enables tool-calling LLMs to search the internet, capture website images, extract webpage text, and more via a local MCP server.

An Operit-compatible adapter of the Exa MCP server, enabling web search, code search, and company research capabilities in AI assistants. It fixes MCP handshake compatibility issues, allowing tools like web_search_exa and web_fetch_exa to load and run reliably.