Browse the catalog

Sparse Mixture-of-Experts (MoE) router and code reasoning engine (Mistral style)

YT-MCP-Server provides a bridge between AI assistants and YouTube content through the yt-dlp tool. This implementation enables assistants to interact with YouTube videos by leveraging the powerful yt-dlp command-line utility for video information extraction and downloading capabilities. Built with TypeScript using the MCP framework, it exposes YouTube functionality through a standardized interface, making it valuable for use cases requiring video content analysis, information retrieval, or media processing directly within assistant conversations.

XLMOracle MCP Server — Stellar intelligence for AI agents

Lightweight self-supervision that piggybacks on your existing memory system.

Enables Codex to clarify requirements via native MCP elicitation controls, supporting single/multiple-choice and free-text questions with recommended answers and a discuss-first option.

Model Context Protocol server for real-time US climate risk and home insurance metrics.

Deploys the Databricks AI Dev Kit MCP server as a Databricks App, exposing over 80 tools for interacting with workspace services like SQL warehouses, Unity Catalog, and AI/BI dashboards. It enables users to manage and query Databricks resources via natural language in the AI Playground using a Streamable HTTP transport.

Provides tools for AI agent persona management, safety verification, and efficient swarm memory synchronization across multiple agents. It enables users to search and install personas while utilizing a token-efficient Git-based workflow for maintaining shared project context.

LLM inference latency, token usage and cost tracer

Researched knowledge for AI agents. Canonical answers from official sources.

MCP Toolz is a context management and todo persistence server designed specifically for Claude Code workflows, enabling seamless sharing of conversation contexts, code snippets, and todo lists across sessions through a shared SQLite database. Built by Taylor Leese, it provides AI-powered second opinions by integrating with both OpenAI's ChatGPT and Anthropic's Claude APIs, allowing users to get alternative perspectives on their saved contexts. The server offers tools for saving, searching, and retrieving contexts by project, session, or tags, along with todo snapshot management that maintains active state across different projects, making it useful for maintaining continuity in development workflows, getting AI feedback on code decisions, and preserving work context between Claude Code sessions.

Coolify-ready self-hosted OpenConnector deployment template for MCP, OpenAPI actions, OAuth connectors, API integrations, and AI automation.

MCP-Tekton is a proof-of-concept server that integrates Tekton CI/CD pipelines with AI assistants. Developed by the OpenShift Pipelines team, it provides tools for starting pipelines and monitoring pipeline runs in Kubernetes environments. The implementation uses Kubernetes client libraries to interact with Tekton resources and includes informers to track pipeline run status changes. It's particularly useful for DevOps teams who want to enable AI assistants to manage CI/CD workflows through natural language commands, allowing for pipeline execution and status monitoring without requiring direct cluster access.

MobOpinions Survey Light as MCP tools: build, target, launch and analyse consumer surveys from Claude, ChatGPT or Cursor (remote server, OAuth 2.1)

The CoRT MCP Server implements Chain-of-Recursive-Thoughts methodology that enhances AI reasoning by making models argue with themselves repeatedly across multiple rounds. Developed by KunihiroS based on PhialsBasement's original work, it features multi-LLM inference that randomly selects different models for each alternative response, enhanced evaluation prompts, and detailed logging capabilities. The server integrates with OpenAI and OpenRouter APIs, supporting various LLMs including GPT-4, Llama, Gemini, and Mistral models. It's particularly valuable for complex problem-solving scenarios where deeper, more thorough reasoning is required to generate optimal responses.

Hard disk drive arm scheduling algorithms: SCAN (Elevator algorithm) and head movement optimization.

A lightweight Model Context Protocol (MCP) server that gives AI assistants direct control over your local VirtualBox environment to manage VMs, snapshots, and guest execution.

Mailchimp via MCP: draft, test, and send campaigns; manage audiences and subscribers; pull reports.

Real-time companion monitor for OpenClaw agents.

Mailgo Campaign Suite MCP Server AI-powered cold email campaign management through Model Context Protocol (MCP). Overview Mailgo Campaign Suite MCP Server connects your AI assistant directly to the Mailgo cold email platform. Through natural conversation, you can verify email addresses, claim pre-warmed mailboxes, launch campaigns, manage their lifecycle, and pull