Browse the catalog

Annotation MCP server that provides persistent note-taking and task management functionality through a JSON file-based storage system. Built by xmarlon30x2, the implementation offers comprehensive page and annotation management with tools for creating, reading, updating, and deleting pages with associated annotations that can be checked/unchecked like todo items. Features include bulk annotation operations, individual annotation management, and automatic UUID generation for all entities, with data stored locally in a configurable JSON file (defaults to ~/notes.json). Designed for users who want structured note-taking and task tracking capabilities integrated directly into their AI workflows, enabling conversational management of personal knowledge bases and todo lists without requiring external database dependencies.

Enables saving structured development ideas as HTML files from Claude Code CLI or claude.ai, capturing titles, summaries, features, tech stacks, phases, and other planning details using provided tools.

An MCP server that exposes FFmpeg as a structured tool set for AI agents, enabling timeline-based video editing, preview, rendering, and analysis with an optional LLM autopilot.

Crea tu servidor MCP con Azure Functions ⚡️🧰

Enables querying Steam item prices, wear, and price history via the SteamDT API, allowing AI assistants to retrieve and analyze Steam marketplace data.

datos.gob.cl provides AI agents with access to the Chilean government's open data portal through a Pipeworx-hosted MCP endpoint using the CKAN API. Agents can search and retrieve datasets from Chile's official public data catalog covering government statistics, public services, and administrative data. The endpoint operates on Pipeworx's free tier with 50 calls per day.

Connects AI assistants to DocuJSON for PDF generation, template management, and API operations via natural language. It enables tasks like creating invoices, managing templates, and viewing usage stats through MCP-compatible tools.

Enables secure Kubernetes operations with configurable security modes, supporting core Kubernetes resources, Istio service mesh, and Helm chart management through natural language.

Compiles TikZ code into high-resolution PNG images, enabling AI assistants to render and preview LaTeX/TikZ diagrams during conversations.

This MCP server provides tools for querying OCI registries and container image references, enabling AI assistants to retrieve image information, list repository tags, and access image manifests and configurations. Built by StacklokLabs using Go with the google/go-containerregistry library and mark3labs/mcp-go framework, it supports multiple authentication methods including bearer tokens, username/password, and Docker keychain integration, with configurable port settings and graceful shutdown handling. The implementation offers four core tools for getting image metadata (digest, size, architecture, OS, creation date, layers), listing available tags for repositories, retrieving raw image manifests, and accessing detailed image configurations, making it valuable for container security analysis, image inventory management, registry auditing, and any workflow requiring programmatic access to OCI registry data.

MCP server for managing PowerDNS DNS records through the PowerDNS-Admin API. Supports listing zones, getting zone details, and creating, updating, deleting DNS records.

MCP server that lists applications and phone numbers, and initiates outbound calls via Fonoster.

Frida MCP provides a bridge between AI systems and mobile/desktop applications through Frida's dynamic instrumentation toolkit. This implementation enables AI assistants to interact with running processes across devices, offering capabilities like process management, device enumeration, JavaScript execution, and script injection. Built with the official MCP Python SDK, it features an interactive JavaScript REPL with real-time execution, comprehensive error handling, and progress tracking for long-running operations. The server is designed for seamless integration with Claude Desktop and supports all MCP transport methods, making it valuable for application analysis, debugging, and security testing workflows.

Enables MCP clients to execute Python code on Google Colab GPU/TPU runtimes via the official Colab CLI, with session, file, and package management capabilities.

Provides live AIS vessel positions from datalastic.com, enabling querying of vessel data through natural language via the Pipeworx MCP gateway.

Selenium Grid MCP server for browser automation (mirror)

Open-source MCP server that audits websites for AI search readiness, providing deterministic scoring (0-100) and prioritized fix lists for metrics like JSON-LD, llms.txt, heading hierarchy, and AI crawler access.

An MCP server for fetching and transforming web content into various formats.

Enables Cursor AI to interact with MySQL databases through natural language, supporting SQL queries, table schema retrieval, and data operations.

An MCP chatbot server that answers questions about a Reinforcement Learning graduate project by dynamically selecting and calling structured tool functions to retrieve precise project data, including training rounds, hyperparameters, and infrastructure details.