Browse the catalog

AI Model Experiments MCP ('Model Lab') — run the same prompts across many

MCP server for the SnapAPI web capture API. Take screenshots, scrape pages, extract structured data, generate PDFs, record videos, and run AI analysis on any URL — all from Claude, Cursor, VS Code, or any MCP client. 9 tools, 30+ device presets, ad/cookie blocking. Install: npx snapapi-mcp

An MCP server that provides LLMs with full read/write access to an Open Knowledge Format (OKF) knowledge bundle, enabling structured, persistent long-term memory.

Provides time-aware greetings in multiple languages and timezones, with personalization support.

Free, open-source screen recording MCP server for AI agents. Enables screen capture, screenshots, and frame extraction locally without cloud dependencies.

A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

Disability insurance quote intake and coverage guidance for high-income professionals. Provides a quote_request action that files a lead with a licensed brokerage, plus read-only tools for specialty guidance, carrier comparison, benefit-cap math, and rider definitions.

A lightweight MCP gateway that aggregates multiple MCP services into a unified stdio interface, automatically prefixing tool names with the service name to avoid conflicts.

A simple Model Context Protocol (MCP) server that allows GitHub Copilot to access custom tools, including an example tool to return the author name.

Implements Anthropic's multi-agent research architecture with subagent spawning, adaptive stopping, and citation processing for automated research.

Gives Claude access to your WHOOP health data including recovery, sleep, workouts, cycles, body measurements, and profile via the WHOOP Developer API.

Spawns Claude agents in isolated Docker containers and composes results using functional combinators (run, par, map, chain, reduce, pipeline). Features monadic ref architecture for lazy output handling, GPU and resource semaphores, natural language type contracts with validation, MCP server passthrough to agents, and full artifact tracing with provenance hashing.

This Dify MCP server, developed as an open-source project, enables integration of Dify workflows with MCP-compatible applications. Built with TypeScript and leveraging the Model Context Protocol SDK, it converts Dify applications into MCP tools, supporting streaming responses and configurable via YAML. The implementation focuses on exposing Dify's AI workflow capabilities through a standardized MCP interface, making it easier to incorporate Dify-powered AI into various applications. It's particularly useful for developers looking to leverage Dify's workflow automation and AI orchestration features within MCP ecosystems, enabling use cases like chatbots, content generation, and data analysis pipelines that can seamlessly interact with other MCP tools and resources.

Provides access to real-time and historical flight data from Flightradar24 API, enabling users to track live aircraft positions, query flight histories, and retrieve comprehensive aviation information including aircraft, airline, and airport details.

Stages local images and videos into SchedulifyX by uploading files out-of-band and returning media IDs, enabling scheduling without passing bytes through the AI context.

Scans repositories to produce a readiness score and actionable fixes across positioning, tryability, community, MCP, and monetization, plus generates launch assets and sponsor-tier ideas.

Research into training a multimodal AI model for parametric CAD design using geometric data, B-rep encoding, and human workflow imitation learning.

Provides public template contracts, examples, and troubleshooting for generating validated local videos from briefs using Remotion templates, without requiring an API key.

Australian and New Zealand PII detection and sanitisation for AI agents, using Microsoft Presidio with custom recognizers for TFN, Medicare, ABN, and more.

A local stdio MCP server that gives Claude (or any MCP client) full programmatic control over a single YouTube channel, including video upload, channel management, comments, analytics, and more.