"Using voice commands to interact with Claude on desktop" matching MCP servers:

Provides a read-only MCP bridge that lets Claude Web inspect workspace files, git state, and recorded test results while Codex remains the sole executor of changes.

Enables LLMs to capture desktop screenshots and control the mouse and keyboard on Linux, including Wayland, through MCP.

An MCP server exposing every documented Email on Acid API v5 request as a tool — 24 tools across authentication, email client lists, email rendering testing, and spam testing.

.FAF (Foundational AI-context Format) with 50+ tools - Only Persistent project context that integrates seamlessly with Claude Desktop workflows. Officially merged (#2759) Anthropic MCP server.

Automates the conversion of Figma designs into TypeScript React components and integrates with GitHub to create pull requests for the generated code. It includes visual regression testing with Playwright and accessibility validation to ensure implementations match the original designs.

MCP server providing code review, auto-fix, test running, linting, formatting, and refactor suggestions for Claude Code.

MCP server that enables Claude Code to send code and plans for review by OpenAI Codex, returning structured feedback inline.

Enables AI agents to start, control, and verify local open.mp/SA-MP game servers via MCP stdio, using a headless RakClient to send allowed slash commands and assert round-trip responses.

Enables Claude to capture screenshots of the screen, windows, regions, and web pages, and compare screenshots for visual regression testing.

Enforces 21 critical rules derived from 96+ documented failure patterns to prevent common AI assistant mistakes. Provides automatic compliance checklists, rule summaries, and auto-updates.

Enables AI-powered automated testing, security scanning, code review, and maintenance tasks directly within Claude Code or desktop.

Enables Claude Code to score its tool-calling transcripts for hallucinated action claims, unsafe edit ordering, redundant tool-call loops, and pass@k across repeated attempts at a task.

MCP server for Claude Text Lab, enabling fact-preserving regeneration of Claude-generated text through inspect, sanitize, audit, rewrite, and benchmark operations, with auditable local quality gates and an unverified provenance verdict.

MCP server for self-hosted qTest Manager, enabling natural-language management of projects, modules, test cases, requirements, traceability, and test execution via the qTest REST API.

Provides a framework for running multiple MCP servers using FastAPI, stdio, and streamable-http transports, with an echo tool for testing and integration with MCP Inspector.

Enables a stateless, horizontally scaled MCP server using the 2026-07-28 specification, with tools for load testing and instance-aware operations.

Automates downloading mobile game performance data from PerfDog and converts it to Tableau-ready CSV format with device statistics, FPS metrics, and time-series data.

Enables migration of test automation projects from WebDriverIO to Playwright using AST-based transformations. Provides tools for analyzing tests, converting syntax, refactoring to Page Object Model, and generating migration reports.

Single MCP server providing over 500 developer tools for Claude Code, covering security, testing, documentation, and more.

MCP server for browser automation with shared authentication and built-in UI auditing.