"CSS" matching MCP servers:

Self-hosted headless CMS with a built-in MCP server: agents create, edit, translate and publish content through the same RBAC, validation and audit log as the admin.

MCP server for programmatic read-only access to RiseUp cashflow data, allowing AI assistants to retrieve budget information via natural language.

Drives the browser you are already signed into, so work behind a login, SSO or MFA needs no scripted auth. A local stdio MCP server talking to the free T3rnel Browser extension over a native-messaging relay. 14 tools standalone; 101 with the extension — CSS-as-component export, full-page capture, React inspector, network and console capture, form filling, record and replay. Nothing hosted.

Read Layerdock website feedback in your coding agent. Each pin comes with the CSS selector, screenshot, page URL and the console and network trace captured when the client reported it. Fix the bug, reply on the thread and mark it resolved without leaving the editor. Works with Claude Code, Cursor, Codex CLI, Windsurf, VS Code, Zed and Antigravity.

Gives every AI agent you use one shared, versioned memory in a local SQLite file, so a fact saved from one app is found by all the others. Runs fully offline with no API key, records which agent wrote each change, and keeps every prior version so nothing is silently overwritten.

Enables AI agents to perform comprehensive person and company lookups by integrating directly with the Lusha API for business contact enrichment. It provides tools for bulk contact identification via LinkedIn URLs, emails, or names, alongside detailed company information retrieval.

Enables AI clients to connect to a selected website via OAuth, send ready-to-use static HTML packages, read and edit text, CSS, and JavaScript with preview, and manage pending updates without automatic publishing.

Enables local MCP access to both Skilljar REST APIs (v1 and v2), reproducing the official 73-tool v2 surface and adding v1-only capabilities such as per-lesson progress, webhooks, asset upload, commerce, learning paths, and instructor-led training. Keeps credentials on your machine via stdio transport.

Provides AI ingress governance by masking prompts, classifying risk, and enforcing tool policies before agent calls reach model providers or sandboxes.

Color conversions math for 205+ color spaces, including OKLCH, CIELAB, CAM16, HCT, Display P3, Rec. 2020, camera logs, print and appearance models. Every space is verified to an authoritative reference. A color goes in as any CSS string or as channel values. Tools: convert, gamut, css, space, spaces, cube, shader, icc and code. No API key, no configuration and no network.

Converts any URL to clean, token-efficient Markdown for AI agents. Strips ads, navigation, and scripts. Supports CSS selectors, batch processing (10 URLs), token counting, and smart caching.

Enables AI agents to perform real-time web search, research, and content extraction using You.com's search infrastructure, with a free tier available.

It turns natural-language requests into Microlink calls: take screenshots, generate PDFs, extract metadata or readable text, detect video/audio sources, run Lighthouse audits, scrape custom fields with CSS selectors and more

Scrape any webpage and return clean markdown, HTML, or structured JSON. Bypasses anti-bot protection, renders JavaScript (React/Vue/Angular), supports premium residential proxies and CSS extraction. Works with any MCP client — no local install required.

Builds and edits real websites from your coding agent: create a site from a template, rewrite sections, add and link pages, insert blocks, keep reusable symbols in sync, screenshot any viewport, and export static HTML/CSS/JS. Drives an open Swebsy Studio tab in your browser over a local 127.0.0.1 WebSocket relay — no account, no API key, and no per-token AI fees.

Enables AI agents to onboard restaurant brands and manage Crave menus, storefronts, and mobile releases via natural language.

Enables AI assistants to interact with self-hosted Dynatrace Managed environments to retrieve observability data, security insights, and performance metrics. It allows users to query problems, logs, events, and SLOs through natural language interfaces in both local and remote modes.

Model Context Protocol (MCP) integration for managing content in the DevHub CMS system (blog posts, content, location administration)

MCP server for fetching, parsing, and managing RSS feeds. Features Fetch and parse RSS/Atom feeds In-memory caching with TTL Batch fetching of multiple feeds Monitor feeds for new items Search content across multiple feeds Extract and format feed content

LUNO is an AI-era backend for humans (Console) and agents (MCP): identity, content, forms, storage, and public APIs — not a website builder.