Browse the catalog

Provides AI agents with persistent memory across sessions, enabling recall of decisions, clients, and deadlines with verifiable citations.

Enables file system operations like listing, reading, writing, deleting, and renaming files within a specified folder via a FastAPI-based MCP server.

Databricks MCP Server provides a bridge between LLMs and Databricks environments, enabling natural language interaction with SQL warehouses and job management systems. The implementation offers tools to run SQL queries, list jobs, check job statuses, and retrieve detailed job information through a FastAPI-based MCP server that connects to the Databricks SQL connector and REST API. It handles authentication via personal access tokens stored in environment variables and formats query results as markdown tables, making it particularly valuable for data analysts and engineers who need to interact with their Databricks workspaces through conversational AI interfaces.

MCP server for Home Assistant — 323 tools across 29 domains: entities, automations, dashboards (sections-aware), Card Builder, energy, ESPHome/LVGL, HACS, Supervisor, git config versioning, BM25 tool search, aggregated snapshot

讓AI助理直接查詢台灣公開資料，包括公司登記、詐騙查核與實價登錄，資料即時且附來源連結。

MCP server for a self-hosted La Suite Docs instance: search, browse, read, create, and edit documents from Claude Code and other MCP clients.

MCP server that provides audit and safety-check tools for enterprise SDLC code integrity, enabling AI agents to scan workspaces for lifecycle gaps, mock-theater tests, DRY violations, and language-specific issues in shell, JavaScript/HTML, and Python.

Optimize AI prompts through a two-layer system combining a deterministic rule engine with optional LLM enhancement. The server provides eight tools for prompt scoring, analysis across five dimensions, iterative optimization, and task decomposition, supporting Anthropic Claude and OpenAI as optional LLM backends.

An interactive web tutorial for learning how to build MCP (Model Context Protocol) servers. This educational website provides step-by-step guidance for implementing and understanding MCP servers.

This MCP server provides a bridge between AI assistants and IssueBadge, enabling integration for issue tracking and badge management workflows. Built as a Node.js Express server using axios for HTTP requests, body-parser for request handling, and uuid for unique identifier generation, it facilitates communication between Claude and IssueBadge's API endpoints. The implementation is designed for teams and developers who need AI-powered assistance with issue management, project tracking, and badge-based workflow automation within their development processes.

A Model Context Protocol (MCP) server that provides access to Japanese weather forecasts using the weather.tsukumijima.net API.

Enables AI agents to simulate network failures and test application resilience in Playwright browser sessions.

Universal MCP Gateway & Bridge for Android Termux (OpenAI Codex, Claude Code, Google Antigravity, Gemini Spark)

Enables students to ask an AI assistant about their Canvas LMS data, including assignments, grades, missing submissions, discussions, and upcoming items, while keeping access read-only and private.

Take Wayland screenshots via grim/slurp. Full screen, region, or interactive crop.

MCP server for overseer.nvim — gives any MCP-capable coding agent running inside Neovim (Claude Code, Codex, Gemini CLI, opencode) the same visibility and control over tasks the user has: list, run, tail, restart, stop. Agent-started dev servers land in the user's own task list instead of becoming invisible orphaned processes.

GenPark AI Agent Skill - AST security pattern matcher for injection vulnerabilities, insecure deserialization, secret leakage, and safe code rewrite synthesis.

A lightweight MCP service that enables programmatic downloading of Instagram videos to a specified local path with progress tracking.

Tree-based navigation MCP that provides a single interface to explore and execute actions across multiple GNOSYS MCP servers, reducing token consumption from ~14k to ~1.4k.

Enables querying MRR, churn, and revenue from Stripe, Gumroad, and Lemon Squeezy directly inside Claude, allowing natural language questions about business metrics.