Browse the catalog

The Patchright Lite MCP Server provides AI models with stealth browser automation capabilities through a streamlined interface. Built by Dylan Groos, it wraps the Patchright Node.js SDK (an undetected version of Playwright) to avoid anti-bot detection systems while offering four essential tools: browse for navigating to websites, interact for performing actions on web elements, extract for retrieving page content, and close for managing browser instances. The server uses the stdio transport for seamless integration with AI tools and is containerized for easy deployment, making it particularly valuable for AI assistants that need to perform web automation tasks without being detected by anti-bot systems.

Enables applying deterministic film grain and analog adjustments to photos locally via natural language, with no uploads.

JSON/YAML/CSV validate, diff, transform for AI agents

Enables interaction with Google Analytics 4 data through the Google Analytics Data API. Built using Google ADK UI and deployed on Google Cloud Platform with proper service account authentication for GA4 data access.

A governed MCP server for integrating AI agents with customer data, featuring role-based access control, field redaction, and human-in-the-loop approval for secure support operations.

Local MCP server for Polish company registries — Biała Lista MF + KRS

Provides persistent memory for AI agents, including context storage, facts, plans, RAG search, code snippets, and conversation compaction, enabling state to survive across sessions and processes.

Free ClickHouse MCP server — free cloud ClickHouse OLAP database for Claude, ChatGPT and AI analytics

An MCP server that provides AI agents access to Granola meeting notes. It enables searching notes, retrieving full content with transcripts, and paginating through meeting history.

Wraps OpenAI's Codex CLI with true parallel task execution, worktree isolation for conflict-free runs, and live monitoring of each task.

A Model Context Protocol (MCP) server for interacting with the Solana blockchain. Provides tools to query balances, transactions, tokens, and network stats.

Built by Vishwajeet Dabholkar, this server extracts clean markdown content from web pages using Playwright's headless Chrome browser. It intelligently identifies main content areas while filtering out navigation, headers, footers, and advertisements, with special optimizations for platforms like Confluence. The implementation supports configurable options including image and link inclusion, custom CSS selectors for waiting, timeout controls, and handles JavaScript-heavy sites by waiting for content to load. This makes it valuable for content analysis, documentation processing, and web scraping workflows where clean, readable text extraction is needed.

Provides persistent memory storage for AI agent sessions with semantic search, knowledge graph triples, and audit trails. Context spaces enable multi-agent collaboration with fine-grained permissions. Replay tools offer time-travel debugging through memory timelines, snapshots, and diffs. Supports both cloud API and local SQLite operation modes.

A Model Context Protocol (MCP) server that provides AI-powered Google search functionality using Gemini.

Database Query Generator Agent Skill. Converts natural language questions into safe, read-only SQL queries.

This MCP server integrates with Together AI's Flux.1 Schnell model to provide high-quality image generation capabilities. Developed by Model Context Protocol, it offers customizable image dimensions, clear error handling, and optional image saving. The server is designed for easy integration with MCP-compatible clients and is ideal for applications requiring AI-powered image creation based on text prompts.

MCP server: convert between YAML and JSON. Preserves keys, arrays, nested structures.

ChatterBox MCP server by Alex Tsimbalistov enables AI agents to join and interact with online meetings across Zoom, Google Meet, and Microsoft Teams platforms through the ChatterBox API. The implementation provides three core tools: joinMeeting for deploying bots to capture meeting transcripts and recordings with configurable bot names and webhook notifications, getMeetingInfo for retrieving session data including timestamps and formatted transcripts, and summarizeMeeting for generating structured meeting summaries from transcript data. Built with TypeScript and the MCP SDK, it integrates with ChatterBox's meeting bot service to provide programmatic access to meeting participation and analysis capabilities, serving teams building AI-powered meeting assistants, organizations requiring automated meeting documentation, and developers creating workflow automation around video conference interactions.

A demonstration MCP server supporting both Stdio and SSE transports, providing example tools (echo, add, time, UUID generation) and resources for learning and testing MCP implementations.

An MCP server for saving project notes and design decisions to a SQLite database, with git-tracked storage and support for categories, tags, and search.