swebsy-mcp
OfficialRelated Servers
Alternatives to swebsy-mcp
- AlicenseCqualityDmaintenanceInteract with Webflow sites, pages, and collections.22877 npm140MIT
- -
Related Servers
- AlicenseAqualityAmaintenanceEnables AI agents to drive the user's already-running Google Chrome through a WebSocket bridge, listing and switching tabs, navigating, clicking, typing, scrolling, extracting DOM, taking screenshots, and evaluating JavaScript. It works without restarting Chrome and preserves all existing logins, cookies, and 2FA sessions.11MIT
- AlicenseAqualityCmaintenanceEnables AI clients to control the user's already-open, logged-in browser pages in real time over a local WebSocket channel, without Playwright, Puppeteer, Selenium, or any browser driver. Exposes tools for navigation, semantic page snapshots, clicking, form filling, JavaScript evaluation, screenshots, network monitoring, cookie handling, and tab management via the CDP.20MIT
- AlicenseNot gradedqualityFmaintenanceStatic site generator / website building toolkit for AI coding agents like Claude, Codex, Cursor, Gemini, OpenClaw, etc. No subscription, no lock-in — host your site anywhere.1 npm9Elastic 2.0

thinhost-mcpofficial
AlicenseAqualityCmaintenanceEnables AI agents to publish static sites and build folders as live websites, push updates, provision and manage custom domains with DNS, and send transactional email. Ships as a local pip/uvx server that reads build folders directly, or as a hosted HTTP endpoint for Claude Code, Claude Desktop, and other MCP clients.11MIT
Plasmateofficial
AlicenseNot gradedqualityBmaintenanceAgent-native headless browser for AI agents. Converts web pages to a Semantic Object Model (SOM) instead of raw HTML — 17x average token reduction across real-world sites (up to 117x on complex pages). Native MCP server with fetch_page, extract_text, extract_links, and full browser automation. No API key required.35 npmApache 2.0- AlicenseCqualityBmaintenanceEnables AI agents and developers to automate real Chrome/Chromium browsers through the Chrome DevTools Protocol, with token-efficient snapshots, multi-action batching, shadow DOM traversal, system-page control, extension management, and network/WebSocket inspection.64MIT
TDQS
Scored across 33 tools
Each tool targets a distinct resource (site, page, section, block, symbol, asset, skill) with clear responsibilities. Cross-references in descriptions (e.g. create_page vs replace_page_content) explicitly disambiguate similar actions. No two tools appear to do the same job.
Tools consistently follow a swebsy_ verb_noun snake_case pattern (list_pages, create_site, edit_section). Minor deviations: `status` and `capture` lack a noun/verb complement, and `get_*`/`read_*`/`list_*` verbs are used interchangeably. Overall the pattern is predictable and scannable.
At 33 tools this is a large surface, exceeding the 25-tool threshold for 'too many'. However, the broad scope (site management, page structure, symbols, assets, settings, guidance) means most tools serve a distinct purpose. The count still feels heavy for an agent to navigate, warranting a below-average score.
The surface covers the full lifecycle of site creation, page composition, section editing, symbol reuse, asset management, and export. Obvious gaps like delete_page or site publish are absent, but agents can work around them via export and other tools. The inclusion of capture and guidance tools adds round-trip verification and learning support.