Browse the catalog

A self-updating MCP system that analyzes design and code inputs with an LLM, refines them through conversation, and crystallizes approved patterns into a local skill library for MCP agents.

Persistent memory for AI agents over the Model Context Protocol (MCP).

Enables AI assistants to create and manage visual automation configurations, workflows, and UI states through the Qontinui API. It supports project management, workflow execution, and configuration handling for automated web interactions.

Provides 50+ tools for interacting with Rippling's HR platform, including employee management, payroll, time tracking, benefits, recruiting, learning, devices, groups, and custom objects, all through natural language.

Provides AI assistants with full access to Metabase analytics platform, enabling dashboard and card management, database queries, and schema operations through natural language.

MCP server for LibreNMS network monitoring

Connects Claude or any MCP client to the Strava API v3, enabling access to fitness data such as activities, athletes, clubs, segments, routes, and streams.

Enables AI agents to access live Zillow property data, Zestimates, and listings for over 160 million U.S. homes.

Generates and validates ISO 20022 Exceptions & Investigations payment cancellation messages (camt.056) with XSD validation.

This Remote MCP Server enables website analysis and content extraction using Cloudflare Workers without requiring authentication. Built with the Model Context Protocol SDK, it leverages Cloudflare's Browser Rendering and AI capabilities to provide two key tools: analyze_website for scraping and summarizing website content, and ask_q_about_website for answering specific questions about web pages. The implementation includes robust error handling, retry logic for failed requests, and browser session management to ensure reliable performance. Ideal for AI assistants that need to access and analyze web content in real-time without maintaining separate authentication systems.

Tokenwaste management

Actor-Critic Thinking MCP Server provides dual-perspective analysis through alternating actor (empathetic/creative) and critic (analytical/evaluative) viewpoints for comprehensive performance evaluation. Developed by Aquarius Wing, it implements a structured thinking methodology that tracks rounds of analysis, balancing subjective understanding with objective assessment to generate nuanced, multi-dimensional evaluations. The server is particularly valuable for evaluating creative works, strategic decisions, and complex scenarios requiring both empathy and objectivity, such as performance reviews, artistic assessments, and iterative creative processes that benefit from constructive feedback combining intention analysis with execution evaluation.

A Windows-only MCP server that gives AI models eyes and hands on a Windows machine, enabling file reading, screenshots, mouse/keyboard injection, and an auto-debug loop with a safety-focused watchdog for protected abort regions.

Exposes Metacritic game, movie, TV, and music review data through MCP tools and resources, enabling LLM hosts to search and retrieve reviews with optional filters.

MCP server for foldkit that exposes the 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client for interaction via natural language.

Enables MCP clients to operate Google Flow through a visible browser, supporting login, project tracking, reference upload, generation submission, and media download with local validation.

Enables ChatGPT agents to read Procore project data and create confirmed daily log notes, with project allowlisting and OAuth.

Git-backed MCP server for creating and maintaining an Obsidian-style markdown knowledge base with full CRUD, search, and git sync.

Your coding agent keeps solving the same problem twice. legendary makes it stop — and tells you when its notes have gone stale.

MCP server that validates dashboardbase setup files and widget endpoint responses against the dashboardbase JSON contract, reporting errors and warnings before deployment.