Browse the catalog

Enables AI assistants to query and manage local PostgreSQL databases through SQL execution and schema exploration tools. It supports both read-only queries and write operations including table creation and data modification via natural language.

The PPTX MCP Server enables programmatic creation and manipulation of PowerPoint presentations through a FastMCP-powered interface. Built with Python 3.12+ and the python-pptx library, it offers tools for creating slides, adding text, shapes, and images, as well as rendering slides to PNG using LibreOffice. The server includes a companion Google ADK agent example that demonstrates visual verification of slide changes. This implementation is particularly useful for automated document generation workflows, report creation, and integration with AI assistants that need to produce visual presentations based on data or user instructions.

A security-first MCP server that generates images via OpenAI's image model (gpt-image-2) and returns them as MCP image content, usable from Claude Code, Claude Desktop, and other stdio MCP clients.

MCP server providing emulator control for a loopback-only DOSBox-X QMP server, with tools for keyboard input, memory reads, screenshots, and state snapshots to complement Ghidra's GDB TraceRMI debugging.

Connect your Clear bank account to AI assistants like Claude and ChatGPT via Open Finance Brasil to query balances, statements, credit card bills, and investments in natural language (read-only).

Enables LLM-powered IDEs to search PyBaMM documentation and source code, with tools for full-text search, reading doc pages, and browsing source files from a local clone.

A Model Context Protocol (MCP) server for Garmin Connect integration. Access your activities, health data, training metrics, and more through Claude and other LLMs.

MCP server for browser automation using chromedp

Enables publishing Facebook Page posts (text and photo) and retrieving page info via the Meta Graph API, with dry-run safety defaults and remote MCP transport.

Enables LLMs to interact with Hopsworks for platform management, feature store operations, model lifecycle, jobs, and integrations.

🤖 Explore Model Context Protocol (MCP) with Google Gemini. TypeScript monorepo covering MCP servers, clients, tool calling, and agentic AI workflows.

Analyzes a local codebase and exposes its structure, per-file summaries, dependency graph, and complexity hotspots as tools for MCP clients like Claude.

Integrates task management with the Pomodoro Technique, enabling AI assistants to manage productivity workflows through timed work sessions, task tracking, and comprehensive productivity statistics.

Enables running commands over SSH on remote Linux hosts, with logging and standalone executable support.

This StockScreen MCP server, developed by Todd Wolven, provides AI assistants with advanced stock screening capabilities using data from Yahoo Finance. Built with Python and leveraging libraries like yfinance and pandas, it offers a flexible interface for technical, fundamental, and options-based stock analysis. The server implements customizable screening criteria, watchlist management, and result storage functionalities. It's designed to handle various market cap categories and ETFs, with robust error handling and rate limiting. This implementation is particularly valuable for financial analysts, algorithmic traders, and AI researchers working on quantitative finance applications, enabling use cases such as automated trading strategy development, portfolio optimization, and market trend analysis.

Provides explicit, governed long-term memory for Claude Code with per-repository isolation. Each git repository maps to its own memory thread, ensuring scoped storage and retrieval. Supports storing general notes, coding preferences, and architectural decisions with full provenance tracking. Memories persist across sessions and are searchable via the Sovant dashboard.

MCP server for sending notifications to ntfy.sh or self-hosted ntfy instances.

An MCP server that provides a permission-aware context layer over team tools, enabling AI agents to recall, search, and write to a shared memory graph with ACL-bound retrieval.

Provides read-only access to PostgreSQL databases, enabling users to list tables, view table structures and statistics, and execute SELECT queries safely through natural language.

Enables LLMs to make HTTP requests with OAuth2, session cookies, retry logic, and cURL command generation, while providing security features like SSRF protection and TLS enforcement.