"A device or tool to control Home Assistant" matching MCP servers:

MCP server connecting Claude/Cursor to Codex CLI, enabling code analysis via @ file references, multi-turn conversations, sandboxed edits, and structured change mode.

Enables AI agents to directly control Figma Desktop via MCP, supporting UI creation, editing, prototyping, and variable management with over 60 tools.

An MCP server that integrates AI agents with Figma, enabling reading and programmatic modification of designs.

Integrates HomeMatic smart home devices (via CCU3, RaspberryMatic, or debmatic) as MCP tools, enabling natural language query and control of rooms, devices, programs, and system variables.

A MCP server for querying the VirusTotal API. This server provides tools for scanning URLs, analyzing file hashes, and retrieving IP address reports.

Provides access to Shodan's IoT search engine API for device search, host intelligence, exploit database, network scanning, and security analysis through natural language.

Enables AI assistants to read and modify Figma designs programmatically through the Model Context Protocol.

A flexible proxy server that aggregates multiple backend MCP servers into a single interface using STDIO or SSE transports. It supports dynamic server management via an HTTP API and utilizes namespacing to prevent tool conflicts across connected services.

A transparent proxy that intercepts high-risk tool calls and requires OTP-based human approval before they can be executed. It acts as a configurable circuit breaker between AI agents and target MCP servers to prevent unauthorized or dangerous actions.

A lightweight MCP server that enables AI assistants to execute local development tools and retrieve system status with low latency over stdio or HTTP.

MCP server for overseer.nvim — gives any MCP-capable coding agent running inside Neovim (Claude Code, Codex, Gemini CLI, opencode) the same visibility and control over tasks the user has: list, run, tail, restart, stop. Agent-started dev servers land in the user's own task list instead of becoming invisible orphaned processes.

Live Japan seasonal travel data from Japan Meteorological Corporation. 12 tools covering cherry blossom (sakura) forecasts, autumn leaves (koyo), fruit picking, flowers, festivals, and 3-day weather. 1,700+ GPS-tagged spots updated daily at 9AM JST. Works via npx or hosted HTTP endpoint — no auth required.

A TypeScript-based server that enables programmatic management of pseudo-terminal sessions. It allows users to spawn, control, and interact with terminal processes in real-time through the Model Context Protocol.

Enables AI assistants to manage WordPress networks through a MainWP Dashboard, including site management, updates, plugin/theme control, and bulk operations via natural language.

Model Context Protocol (MCP) server for GitLab — exposes 1006 GitLab REST & GraphQL API operations as MCP tools (42 meta-tools / 57 enterprise), 24 resources, 38 prompts, and 17 completion types for AI assistants. Written in Go, single static binary, stdio and HTTP transport.

This MCP server provides comprehensive Google Workspace integration (Gmail, Drive, etc.) with multi-user OAuth. Unique features include RAG-powered natural language to Chat card rendering, runtime Jinja2 macro creation, and dynamic tool management.

Enables AI assistants to search live jobs, view full details, save and track applications in a Kanban board, set follow-up reminders, and subscribe to job alerts—no account needed for searching.

Standalone MCP server for Obsidian vaults - hybrid search (FTS5 + vector + cross-encoder reranking), images and PDFs in agent-readable form, Kanban-aware tasks (Tasks-plugin + Dataview formats), structured memory with topic recall, fine-grained read/write tools for optimal token efficiency, and link graph support. Run locally, self-host, or one-click deploy for remote access. OAuth 2.1.

Operations toolchain for SQLite, Cloudflare D1, and Turso. Every command is available as both a CLI and an MCP tool: inspect, diff, migrate, monitor, back up, and repair databases. 22 stdio tools, read-only by default.

Fetches YouTube video transcripts, using free captions when available and falling back to Gemini-based transcription for missing or broken captions.