"Using npx to run tools directly without requiring an API" matching MCP servers:

A powerful MCP server for fetching and transforming web content into various formats (HTML, JSON, Markdown, Plain Text) with ease.

Enables fetching weather forecasts for the USA via NWS API and for Israel via browser automation using Playwright.

Full-stack utility API with 337+ tools including AI chat, web scraping, weather, finance, SEO, crypto, colors, readability, DNS, and more — all through a single MCP server. Pay-as-you-go credits, no API keys needed.

Enables AI agents to extract structured content from URLs, search the web via DuckDuckGo, monitor site availability, and convert HTML to markdown without requiring API keys.

Enables AI agents to fetch one or many web pages concurrently and receive clean, LLM-ready Markdown with navigation, ads and boilerplate stripped away, plus extracted metadata such as title, description, author, Open Graph tags and canonical URL. It runs locally over stdio with no API key or account, requiring only a single command.

Provides web automation utilities, including taking Camofox browser tab screenshots and saving them directly to local files.

MCP server and agent skill for the pline.ai API: scrape, crawl, batch-scrape, map, and search the web from Claude, Cursor, Codex, and any MCP client.

Enables AI agents to capture any public URL as PNG, JPEG, or PDF via REST API or MCP tools, including screenshot capture, page description, and PDF rendering.

Gives any AI agent two web capabilities: ranked search results with titles, URLs, dates and excerpts via Exa, and clean Markdown extraction of a page's main content with navigation, scripts and footers stripped. Responses are structured and schema-declared, and URL fetching is hardened against private addresses, redirects and DNS rebinding, so agents can research and cite sources safely across MCP clients.

Enables users to discover jobs by target titles and countries, rank job descriptions by skill coverage across all imported resumes, generate tailored ATS-ready resumes and cover letters, and fill and submit requested application batches through a signed-in AI host with browser access.

Exposes 89 hosted, pay-per-call tools that let agents capture screenshots, scrape and search the web, convert and extract PDFs and documents, run OCR, handle text-to-speech and speech-to-text, process images, and parse invoices, contracts and compliance checks. Billing is flat per call and charged only on success, with cost and remaining balance returned in each response.

Give your AI agents a real Chrome on your own Linux server. Connect through MCP or REST, watch live, take over for login and 2FA, then hand control back. Keep encrypted saved sessions, upload files and receive downloads. Open source under AGPL-3.0, with no usage fees; you provide the server.

It enables AI agents to call a small set of reliable, permission-aware tools generated from an existing website through the Model Context Protocol, without rebuilding the site.

A multi-function Streamable HTTP MCP tool aggregation server that provides web search via Brave, Exa, and SearXNG with multi-key rotation and cross-provider fallback, and supports extensible tool families (URL fetch, code search, RAG) through a pluggable architecture.

Enables AI agents to validate AI infrastructure claims, check endpoint availability, solve CAPTCHA challenges, convert web pages to Markdown, search the web, extract structured JSON, and fetch bot-protected HTML through native tool calls.

Enables users to record, review, verify, and expose permitted browser workflows as callable MCP tools with typed inputs, isolated Chromium verification, and approval-gated writes.

Enables AI agents to convert HTML content into clean Markdown, stripping scripts and styles while preserving headings, links, lists, and images, with pay-per-call x402 micropayments and no API keys.

Local-first MCP server that gives Claude Code web search, page reading, video transcription, and image analysis — without paid API keys. Runs SearXNG + whisper.cpp natively on Apple Silicon for zero-cost, low-latency research workflows.

A self-hosted MCP server providing private web search, web page fetching, and current date/time tools, powered by a bundled SearXNG instance for API-key-free local search.

Enables converting webpages into structured JSON using CSS-selector schemas, with anti-bot handling and support for protected pages.

Enables converting any webpage to clean LLM-ready markdown, with extraction, article, and news modes, using a real browser with anti-bot handling.

Provides pre-fetch routing intelligence for AI agents by recommending the cheapest reliable route (HTTP, browser, machine endpoint, or avoid) before visiting a URL.

Fetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.

MCP server that converts web page URLs to Markdown via the Zyla API.

Sub-15ms edge intelligence tools for Claude Desktop, Cursor, and LLM agent loops. Provides sub-millisecond LLM JSON repair, web-to-markdown token compression (cuts context tokens up to 90%), PII redaction, and RFC 5322 B2B email deliverability verification at zero marginal token cost.

Enables AI tools to interact with browsers for enhanced frontend development, providing context to LLMs through tools like API call analysis, screenshots, element selection, and documentation ingestion.

Provides web access capabilities for LLMs including search, fetching, content extraction, PDF reading, image viewing, and screenshots.

An MCP server that provides Claude with comprehensive desktop automation capabilities including browser control, window management, and native mouse/keyboard input on Windows. It enables users to capture screenshots, launch applications, and interact with the system clipboard through natural language.

Provides local web search and content fetching capabilities for AI assistants, enabling them to search DuckDuckGo and extract clean text from web pages. All requests originate from the user's machine to ensure direct network control and bypass external proxies.

Exposes OpenClaw tools (web search, page fetching, browser automation, PDF analysis, messaging, inter-agent communication, Canvas) as MCP tools for ACP agents.

Fetches website content and converts it to Markdown format with AI-powered content cleanup, ad removal, and full OpenAPI/Swagger specification support for easy processing by AI assistants.

MCP server exposing web_search, web_fetch, and cluesift_domain_fetch tools with configurable Ollama API keys and HTTP or stdio transport.

Integrates Jina AI Search Foundation APIs to provide web page content extraction and search capabilities. It supports automatic pagination, result caching, and both standard and VIP search endpoints for enhanced information retrieval.

Playwright browser automation tools for MCP enabling navigation, interaction, content extraction, and semantic locators.

Enables capturing browser API traffic via CDP and turning any website into a ready-to-run FastMCP server, with no official API required.

Provides web connectivity tools for searching the web via DuckDuckGo or SerpAPI, fetching URL content, and extracting readable text from web pages.

Provides LinkedIn automation via a real browser session using your own cookie, enabling profile, company, job, and post search and reading, plus sending messages and connection requests with rate limiting.

This application is a powerful browser monitoring and interaction tool that enables AI-powered applications via Anthropic's Model Context Protocol (MCP) to capture and analyze browser data through a Chrome extension.

Enables ChatGPT plugins and other MCP clients to fetch live web pages and documents as Markdown and to call HTTP APIs via self-hosted Cloudflare Workers.

Enables ChatGPT to invoke native OpenClaw browser operations directly through an MCP connection, forwarding actions to the local Gateway while preserving runtime errors and providing a local call monitor.