"cursor" matching MCP servers:

Enables Cursor to drive Google Chrome through the jev-browser-use click loop, with Cursor supplying tasks, typing text, and verifying results while Jev chooses the next click.

Enables any MCP client to run Cursor's server-side web search as a tool, returning summarized answers with source links. Authenticates via API key or browser-based OAuth login without needing the cursor-agent binary.

Enables AI agents to control Cursor IDE's built-in Browser Tab through a stdio MCP interface, providing accessibility snapshots with refs, click/type/fill, wait conditions, screenshots, and console/network inspection.

Demonstrates using Playwright with the Model Context Protocol (MCP) to enable large language models to automate browser interactions, with an example of cursor-based pagination against the GitHub GraphQL API.

Let Claude, Cursor or Cline fetch pages and run Google searches from a real Singapore mobile IP (Singtel/M1). Hosted; free 24-hour trial key.

An MCP server that provides web search powered by DeepSeek's native search API, returning AI-generated answers with source links. Integrates with MCP-compatible clients like Claude Code and Cursor.

Enables Claude Desktop, Cursor AI, Windsurf, and autonomous LLM agents to scrape, crawl, map, search, and extract validated JSON from live web pages with dynamic rendering, anti-bot bypass, and Markdown conversion.

Job-search agent for any field: finds jobs that match your settings, applies on employer sites through your own AI app (Claude Code, Claude Desktop, Cursor, VS Code), tracks every application in a local dashboard, and checks Gmail for replies. Your data stays on your computer; duplicate checks, submit throttling, and a truthfulness check on cover letters are enforced by the tools. Free.

MCP server for Octen Extract that turns any URL into clean, LLM-ready markdown, with highlights and classification. Works with Claude, Cursor, VS Code, and other MCP clients.

Sub-150ms clean Web-to-Markdown extraction, autonomous agent live web search, and neural speech synthesis for Claude Desktop, Cursor, and Windsurf.

Enables any MCP-compatible AI coding client such as Claude Code, Codex, or Cursor to run web searches and fetch pages as Markdown through a self-built search engine, with per-day and per-month spend caps, prompt-injection fencing on retrieved content, and local usage/cost reporting. Search results can be filtered by site, language, and date, and repeated page fetches within a short window are not billed twice.

Enables MCP clients such as Claude and Cursor to fetch raw page HTML and structured data for products, real estate listings, hotels, groceries, search engine results, and public social media profiles and posts. Tools accept a URL with optional JavaScript rendering and premium proxy options, with failed requests refunded and pending social scrapes retrievable later.

An APAC-native web scraping API for AI agents that provides tools for scraping, crawling, searching, and extracting structured data from websites, directly usable from MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.

MCP server for AI-powered web research — search (Google, Brave, Serper, SearXNG), scrape any page, extract PDFs/DOCX/YouTube transcripts, academic & patent search. Single Go binary. Works with Claude, Cursor, Copilot, and any MCP client.

Gives MCP clients such as Claude Code, Claude Desktop, Cursor or Codex a read_page tool that fetches a web page and returns only its main content as lean Markdown, stripped of navigation, ads and tracking. Accepts optional focus, links and country arguments so a client can pull just the sections relevant to a question, shorten same-site links, or read pages as they appear in a given country.

Bridge between VisBug and Cursor via MCP, enabling visual edits on localhost to be captured and applied as structured CSS diffs. Russian localization of mambari/visbug-mcp.

Enables AI agents in Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI and Codex to scrape web pages into Markdown, text, HTML, JSON or PDF, extract structured data with selectors or autoparse, capture screenshots and PDFs the model can see, drive pages with typed browser actions, keep logged-in persistent browser sessions, and batch-scrape thousands of URLs as async jobs. It also exposes usage, request-log and documentation tools so agents can check costs, diagnose failures and look up parameters without leaving the chat.

The interface protocol for AI agents. 8 kernel primitives + 16 stdlib operations to operate any interface. Forge once, run forever — zero AI at runtime. 81 skills across 41 sites.

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.

Give your AI agent a full Chrome workspace. 70 MCP tools powered by nodriver: browsing, forms, screenshots, data extraction, network capture and passive security checks. Reuse logins, run isolated browsers, and choose a fresh tab, favorite URLs or automatic tab restoration. Direct CDP control without ChromeDriver. One-command setup for 15+ clients including Claude, Cursor and Codex.