"KDE Plasma" matching MCP servers:

Enables MCP clients to inspect and operate desktop application UI elements through platform accessibility APIs and simulated input, without relying on screenshots, across KDE Plasma Wayland, Hyprland, and Windows under a per-app allowlist.

Enables an MCP client to read conversations and send SMS from your own number through a paired Android phone over KDE Connect on the local network, with no cloud relay or gateway account. It exposes thread listing, message reading, contact lookup, and sending tools that hand requests to the phone via D-Bus.

A stdio MCP server that lets AI agents inspect windows, read and click on visible on-screen text, type, press keys, scroll, open apps, and run saved screen-recognition flows on a KDE Plasma Wayland desktop — either the user's own screen or an invisible second desktop. Every input is validated against what is actually on screen at that moment, with sensitive buttons and payment pages held for human approval in a panel the agent cannot reach.

Enables MCP hosts to safely control Douyin developer tools for tasks such as opening projects, previewing, building, capturing screenshots, reading console errors, uploading, and auditing mini programs and mini games.

Enables AI assistants to prepare the SUAP IFMA Work Individual Report (RIT) by gathering receipts, organizing them by semester and topic, drafting the narratives, and leaving the report as a saved draft for review, without ever submitting it.

A Python application that automatically generates different types of mind maps (presentation, comparison, beginner/intermediate content, problem analysis, and review) to help organize ideas visually through Claude Desktop integration.

A template for creating custom tools for Cursor IDE using Model Context Protocol (MCP), allowing developers to extend Cursor's functionality with their own server-based tools.

Enables AI-powered image generation and editing with Nano Banana, plus professional video creation with Veo3, all through Kie.ai's APIs. Includes task tracking, status monitoring, and 1080p video upgrades.

Enables a virtual assistant to look up a contact's assigned agent by department from a Google Sheets roster and route conversations accordingly, falling back to department-only transfer when no match exists.

Enables AI assistants such as Claude or Notion AI to book working hours, query time accounts and absences, and read project-management data in the projo controlling software using each user's own account. Works by automating projo's web interface over HTTP with encrypted per-user sessions, exposing everything as MCP tools.

Self-hosted MCP gateway that connects Claude, ChatGPT, and other AI agents to 20+ enterprise tools (GitLab, Jira, Notion, Google Workspace, Slack, Grafana, …) with OAuth, audit logs, and zero data leaving your infrastructure

Enables users to browse, search, filter, and select project skills through an interactive interface, then confirms the selection so the chosen instructions and customizations are applied to the site project.

Enables AI agents to prepare job-tailoring prompts, export tailored resumes to Google Docs, inspect job details, and retry pending evaluations through JSON-RPC 2.0 tools.

Enables extraction of text, tables, and structured data from PDFs, images, and office documents using LandingAI's Agentic Document Extraction API. Supports both direct parsing and background job processing for large files with privacy-focused processing.