Browse the catalog

This MCP server enables AI agents to search, discover, and install skills from the SkillsMP marketplace, with support for keyword and semantic search, skill content retrieval, and installation to various coding agents.

LLM cost optimization and provider usage visibility for MCP-capable agents.

Tracks a company's long-form publication cadence per month and trend (accelerating, steady, declining, dormant) from a given domain. Provides detailed metrics like post counts, trend percentage change, formats detected, and reliability flags.

Enables security scanning of source code and Apple configuration files, providing evidence-based findings, explanations, remediation plans, threat modeling, and knowledge base access through MCP tools.

An MCP server that provides live geospatial data such as geocoding, POI search, isochrones, and area density from open data sources to LLM clients like Claude, Cursor, or Claude Code.

This Codeforces MCP server by Mohamed-hanfy provides AI assistants with direct access to the Codeforces competitive programming platform's API, enabling retrieval of contest information, user profiles, submission histories, and rating changes through natural language interactions. The implementation wraps the official Codeforces API with async HTTP requests and comprehensive error handling, offering tools for contest analysis, user performance tracking, and submission monitoring. Built for competitive programmers, coaches, and analysts who want to incorporate Codeforces data into AI-powered workflows for performance analysis, contest preparation, and competitive programming insights without manually navigating the platform's web interface.

A Model Completion Prompt (MCP) plugin that allows users to create events in Google Calendar with customizable attributes like times, description, location, attendees, and timezone.

Version-aware AdonisJS documentation MCP server that detects your project's AdonisJS version and provides search and retrieval of relevant docs including core, Lucid ORM, Edge, VineJS, and Japa.

MCP server that provides access to the PeeringDB peering ecosystem database, enabling AI agents to query peering data through natural language.

Enables Claude to use Fabric's AI patterns for content analysis, summarization, learning, coding, and security analysis via MCP.

Open source MCP hosting - deploy MCP servers to HTTP endpoints for n8n, Dify, Voiceflow, and any MCP client.

MCP server that finds open-source, commercially-usable icons and returns direct SVG download links, searching over 300,000 icons with license filtering.

An MCP server that gives AI agents the ability to profile a CSV, define an ML task, tune XGBoost and LightGBM with Optuna, and produce a markdown report with feature importance, all from natural language.

Enables AI agents to manage Google Ads campaigns (Search and UAC) through natural language, with read tools always available and guarded write operations for budgets, campaigns, ad groups, and keywords.

Generates frontend UI code from text descriptions, screenshots, or iterative refinement using Gemini 2.5 Flash.

Live used-car stock on named NZ dealer yards, over MCP. Search make/model/price/city. Not Trade Me.

This Epsilla MCP implementation, developed by Eric from Epsilla, integrates the pyepsilla library to provide a standardized interface for interacting with Epsilla databases. Built with Python and leveraging the Model Context Protocol SDK, it offers tools for creating, deleting, and listing tables, as well as inserting, querying, and deleting data. The implementation abstracts the complexities of Epsilla's API, enabling AI systems to easily manage and manipulate data within Epsilla databases. It is particularly useful for applications requiring programmatic database operations, facilitating use cases such as dynamic data storage, retrieval, and management in AI-driven systems that need efficient vector database capabilities.

MCP server for my tools like OpenERZ or tecdottir.

MCP server that wraps the Wikidata API, enabling AI agents to query and interact with Wikidata data using natural language through the Pipeworx gateway.

A locally-hosted MCP server that provides AI assistants with advanced web crawling capabilities, including structured data extraction, deep site crawling, and page screenshots. It enables users to convert single or multiple URLs into clean Markdown content for processing by LLMs without requiring external API keys for basic features.