Browse the catalog

Flux-Cloudflare-MCP enables AI assistants to generate images through the Flux API running on Cloudflare Workers. Developed by Hzzy2O, this implementation provides a streamlined interface for text-to-image generation with customizable parameters including prompt, dimensions, aspect ratio, and inference steps. The server handles the entire workflow from API communication to image retrieval and optional local file saving, making it particularly valuable for creative workflows requiring image generation without leaving the conversation context.

A TypeScript MCP server boilerplate providing example tools and resources for rapid development and testing of Model Context Protocol servers.

Securely connect AI assistants to PostgreSQL databases with read-only access, schema discovery, querying, and performance analysis tools.

It gives Claude Code, Cursor, and Codex structured workflows and an MCP server for building data pipelines with dlt - covering REST API ingestion, transformations, data quality, and exploration.

This repository contains everything you need to run: A MCP Server, an Ollama LLM Server, a LangChain agent that connects to the MCP server and allows you to interact with it.

This Eufy RoboVac MCP server provides comprehensive control over Eufy robotic vacuum cleaners through local network communication, featuring automatic device discovery via network scanning and ARP table analysis to identify RoboVac devices by their Anker/Eufy MAC address prefixes and open Tuya protocol ports (6668, 6667, 443). The server offers 24 tools covering all major vacuum operations including cleaning control (start, stop, pause, return home), configuration management (work modes, suction speeds), status monitoring (battery level, error codes, work status), and device location features, with intelligent fallback mechanisms that attempt auto-discovery when manual IP configuration fails. Built using the eufy-robovac library, it's particularly valuable for smart home automation, voice assistant integration, and AI-driven household management where users need programmatic control over their cleaning routines without requiring manual device configuration.

This YouTube MCP server, developed using TypeScript and the Highlight AI MCP SDK, enables AI agents to extract transcripts from YouTube videos. It provides a standardized interface for retrieving transcript text from various YouTube URL formats, including standard, shortened, and embed links. The implementation focuses on simplicity and error handling, offering functionality to fetch English transcripts from videos with captions enabled. It's particularly useful for applications requiring automated content analysis, such as sentiment analysis, topic extraction, or summarization of YouTube videos, without directly dealing with YouTube's API complexities. The server supports Node.js >=18.0.0 and uses the youtube-transcript library for transcript retrieval, making it a practical solution for integrating YouTube content into AI-driven workflows.

MCP server that wraps Meta's Messenger Platform, Instagram Messaging, and comment moderation APIs as semantic tools for LLM agents to read inbox, reply, and moderate comments.

MCP server for looking up Danish vehicle information by registration number or VIN via MotorAPI.dk, including vehicle details, environmental data, equipment, and API usage.

MCP server connector for Pinterest — search pins, manage boards, save pins, and follow users via Playwright browser automation.

Enables AI agents to interact programmatically with Claude Code CLI, managing sessions, streaming outputs, and handling permission requests.

An MCP server for manipulating Excel files that features a headless engine for real-time formula calculation and data validation. It enables users to create, read, and manage workbooks, sheets, and charts without requiring Microsoft Excel installed.

Implementation of the Model Context Protocol (MCP) bridge connecting Claude Desktop to the Splunk Management Endpoint. The final solution utilizes a custom-engineered JSON-RPC Relay to bypass legacy protocol restrictions on Splunk Port 8089.

The Astro Docs MCP server provides AI assistants with direct access to Astro documentation, enabling them to help users with Astro-related tasks. Built in TypeScript, it exposes documentation sections as resources with URIs, offers a search tool for finding relevant content, and includes curated prompts for common Astro questions. The server organizes documentation by categories like core concepts, configuration, and deployment, making it valuable for developers seeking assistance with Astro's component-based architecture, content management features, or deployment options without leaving their AI assistant conversation.

Enables AI coding agents to reserve unique AL object IDs via the ALRM database in Business Central, ensuring consistent ID allocation across team members.

Remote MCP Server for listing and getting the menus of the official mensas in munich

MCP server for searching cosmos.so, returning direct CDN image URLs without page scraping.

A read-only MCP server for interacting with Coda API, enabling listing documents, pages, tables, rows, and retrieving page content as markdown.

MCP Database Server provides a bridge between AI assistants and databases through natural language, currently supporting MongoDB operations with plans to expand to PostgreSQL, CockroachDB, and Redis. Developed by Manpreet Singh, this TypeScript implementation uses the Model Context Protocol SDK to expose tools for listing collections, querying documents with filters, inserting and deleting records, and executing aggregate pipeline operations. The server connects to MongoDB via environment variables and handles database operations efficiently, making it valuable for users who need to interact with their databases directly through AI assistants without writing complex queries.

Submit URLs for instant indexing via IndexNow and Google Indexing API.