Browse the catalog

Ankr Agent RPC — MCP server for blockchain data. Public home: install, usage, tool reference.

Monorepo dependency cycle resolver and topological build-order planner using Tarjan SCC and Kahn algorithms.

Generate professional freelance contracts, SOWs, and NDAs for client projects.

A simple implementation of Model Context Protocol server with calculater functions for me to understand the concept of mcp servers

Build a calm, gradient progress bar for Python terminals with eased motion and refined typography.

Agent checkpoint state persistence & crash replay restorer (LangGraph)

Dynamic browser sandbox E2E test synthesizer & HAR verifier (Playwright style)

Enables searching, retrieving, and parsing academic papers from arXiv, including keyword search, PDF downloads, content extraction from HTML/PDF formats, and accessing the latest AI research papers.

A starter template for building Model Context Protocol (MCP) servers with mcp-framework. It includes an example tool and CLI for adding more tools.

Windows screen capture MCP server with display, region, and active-window capture tools.

Enables management of BTRFS snapshots via Snapper and monitoring of BTRFS filesystem health through the Model Context Protocol.

Autonomous prompt loss gradient & few-shot exemplar compiler (DSPy / TextGrad)

Multi-step deliberative reasoning search graph verifier (Perplexity Pro style)

A script-based local MCP server demonstration. The server is built in Bun and runs in VS Code Copilot Chat in agent mode.

Provides AI agents with real-time web capabilities including live search results, markdown web scraping, business lead generation, and detailed company information. It enables agents to bypass knowledge cutoffs by accessing current web data through a monetized Apify Actor.

GenPark AI Skill - Score draft social copy interaction rates based on layout features

A modular MCP server that provides tools for looking up country and state information. Designed as a demonstration of building extensible MCP servers with custom tool modules.

This Mozilla Readability Parser MCP server, created by Max Zimmer, extracts and transforms webpage content into clean, LLM-optimized Markdown. It uses Mozilla's Readability algorithm to remove ads, navigation, and non-essential elements while preserving core content structure. The server converts HTML to well-formatted Markdown, returns article metadata, and handles errors gracefully. It integrates with the Model Context Protocol, allowing AI assistants to fetch and parse web content efficiently. This implementation is particularly useful for reducing token usage in LLM processing, ensuring consistent formatting, and providing clean, relevant content for tasks like summarization, analysis, or information extraction from web pages.

The Doginals skill enables users to interact with the Doginals and Dunes protocols, facilitating inscription.

Provides a secure workspace for AI-driven file management and Python script execution designed to run on Vercel. It enables tools for full file operations and code execution within a sandboxed environment.