Browse the catalog

Enables encoding JSON into compact TOON format and decoding TOON back to JSON, reducing token usage for LLM prompts.

Thin stdio proxy to Pifini's hosted MCP server (real events, reviewed places, and ticket checkout across the Caribbean & Latin America). MIT, zero dependencies.

Semantic tool selection proxy for MCP servers — LLM sees 2 tools instead of dozens

Run Offensive360 SAST scans (60+ languages) on local code; findings with file/line and fixes

Agentic Customer Onboarding Skill. Welcomes new organization signups and generates custom checklists.

Learning MCP Client & Server with Spring AI + Claude. A small two-module learning project that shows how the Model Context Protocol (MCP) works end to end with Spring AI, Java 25, and Anthropic Claude.

Spawn multiple specialized Codex agents as MCP servers, each independently configured.

Provides a audio/video creation toolbox via MCP protocol, enabling natural language-based video editing tasks such as image-to-video, video merging, subtitle extraction, and more.

A model-agnostic MCP server exposing example tools (add1, multiply2, greet) for learning purposes, working with any LLM through stdio transport.

MCP server that connects AI assistants to Telegram as a real user account via MTProto — send messages, manage chats, transfer media, and more

Python cli tool using mcp protocol and llama-8b using groq api to calculate roots of a quadratic eqn.

This MCP server connects to a Linkwarden instance, enabling semantic search, filtering, and management of bookmarks through natural language.

A read-only MCP server for the Little Green Light donor CRM. It lets Claude answer questions about donor data, gifts, and fundraising metrics by querying LGL directly.

Enables generating PlantUML diagrams directly from Claude Desktop, with tools to render, save, and obtain URLs or ASCII art.

AFL (Australian Football League) fixture, ladder, and crowd-sourced tips

A lightweight Spring Boot-based task management server that provides a RESTful API for creating, retrieving, updating, and tracking tasks with AI integration. Built as a template project, it demonstrates best practices for Spring Boot development, including dependency injection, exception handling, and tool-based AI interactions. The implementation uses an in-memory task repository and includes comprehensive unit and integration tests to showcase a clean, modular approach to building MCP-compatible services.

MCP server: extract eTLD, eTLD+1, and subdomain using the Public Suffix List.

AgentGuard (shuaicongxiaomai) scans AI agent projects for leaked secrets, known CVEs, and vulnerable dependencies using the free OSV.dev database, running in isolated Docker containers for security checks before code ships.

An MCP server that tracks the historical changes of Twitter usernames—frequent screen name changes in crypto projects can be a red flag for potential scam risks.

A comprehensive toolkit for building AI agents with blockchain capabilities, enabling interactions with multiple blockchain networks for tasks like wallet management, fund transfers, smart contract interactions, and cross-chain asset bridging.