"Systems or platforms that support dynamic registration" matching MCP servers:

An MCP server that allows users to run and visualize systems models using the lethain:systems library, including capabilities to run model specifications and load systems documentation into the context window.

Dynamic MCP server for Node.js enabling runtime tool creation, management, and execution in isolated sandboxes (Docker or Node).

A dynamic MCP server that automatically discovers Python files in a directory and exposes them as tools to any MCP-compatible AI client, allowing users to easily create and deploy custom AI tools.

Enables AI agents to dynamically register and query MySQL-compatible databases at runtime with built-in destructive SQL protection.

Turns any verb Registry into a real MCP server, where each verb becomes an MCP tool with its own Zod input/output schemas (zero drift).

A simple MCP server implementation in TypeScript that communicates over stdio, allowing users to ask questions that end with 'yes or no' to trigger the MCP tool in Cursor.

MCP-ORTools integrates Google's OR-Tools constraint programming solver with Large Language Models through the MCP, enabling AI models to: Submit and validate constraint models Set model parameters Solve constraint satisfaction and optimization problems Retrieve and analyze solution

A FastMCP server that dynamically loads tools from Python/YAML file pairs, acting as a stand-in for the Tools Framework in agentic-assembly-framework.

Enables AI assistants to execute code in isolated sandboxes with support for Python, JavaScript, and TypeScript, featuring intelligent caching and semantic search for code reuse.

Enables a bot to inspect, query, create, edit, and script Roblox Studio instances in token-cheap batches, plus run Luau, playtests, screenshots, and inputs through Roblox's official Studio MCP connection. It runs locally over stdio or an authenticated local HTTP endpoint, returning small structured answers instead of dumping whole games into context.

MCP server that gives AI assistants a secure gVisor-isolated sandbox to run Python or JavaScript code, returning stdout, stderr, and exit codes without local access.

A professional implementation of a Model Context Protocol server that enables integration between DaVinci Resolve video editing software and AI assistants like Claude Desktop or Cursor.

Manages a Neo4j knowledge graph of reusable Python functions, documentation, and environment variables, enabling dynamic script composition and execution with automatic dependency management and secret protection.

An MCP server that enables AI clients to execute shell, Python, and Node commands on the local machine across platforms.

A production-grade MCP server providing a persistent Python REPL with multi-session support, sandboxing, and timeout protection, enabling LLM agents to execute Python code across multiple turns with variables that persist between calls.

Cloud GPU rendering for Blender, built for AI agents. Preview .blend files or bpy scripts, estimate render time, and render images, animation frames, or MP4 videos without a local GPU. Connect via MCP (OAuth) with Claude, ChatGPT, Codex, or Cursor: https://render.janction.jp/mcp. Get ¥100 in credits without a card, plus ¥400 after card registration. Then ¥0.1 per GPU-second.

A governed registry of reusable Python tools for AI agents, enabling search by intent, execution with JSON input, draft registration, and lifecycle management.

Enables MCP clients to connect to SAP S/4HANA on-premise systems, providing developer-grade read and write access to ABAP source, DDIC objects, table data, syntax/ATC checks, debugging, and transport management.

A local Model Context Protocol server that allows LLMs to securely execute shell commands on remote Linux and Windows systems via SSH connections.

MCP server that enables AI assistants to run multi-step agent pipelines (e.g., Issue Analyst → Code Writer → Test Runner → PR Opener) from conversations, with support for Devin, shell, Python, and HTTP agents.