"How to run code using Claude Desktop" matching MCP servers:

A runtime-free MCP server that converts source code into AST🌲, regardless of language.

Your AI agent can't touch Stripe, Gmail, Slack or more, without your tap. mild.run intercepts every sensitive action and sends you a notification to approve or block — before anything executes. Agent never holds credentials.

An MCP server that gives orchestrator agents fine-grained control over interactive Claude Code sessions running inside tmux, enabling mid-session steering, interruption, and token-efficient result extraction.

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

Windows desktop-control MCP server: screenshot, window mgmt, mouse/keyboard input, recording.

Allows AI clients to see and control Windows 10/11 desktops via MCP, with screenshots, UI Automation, Chrome CDP, keyboard/mouse, and terminal using semantic element targeting.

Provides a personal hybrid running and strength training coach that integrates with Intervals.icu, offering 28-day plans, activity reconciliation, and delivery of scheduled workouts to calendars via MCP.

Enables agents to convert Markdown into WhatsApp-compatible formatting, including styled text, lists, and tables that fit a phone's monospace width.

Windows desktop automation MCP server — screenshot, mouse, keyboard & UI Automation. Lets LLM agents see and control your Windows desktop directly.

Enables search, analytics, and visualization of Claude Code sessions with MCP tools for session management, recovery, and insights.

Enables real-time cross-machine communication for Claude Code agents using a shared MCP relay server.

Post-hoc session handoff and project memory for Claude Code: MCP tools list_sessions and handoff turn any session — even crashed or usage-limit-hit ones — into a clean handoff.md another model can continue from, with secrets redacted from every output. Zero dependencies, fully local; also distills a project's entire session history into one cited memory brief.

Enables searching and retrieving Claude Code conversation history via hybrid semantic and keyword search, allowing the agent to access its own past interactions.

Relays messages between two Claude Code sessions running on separate machines, using the Channels API to push an incoming message directly into the other session so one session can ask another about its own checkout. Each message carries an id and is tracked as sent, delivered-to-process, or answered, with a per-message reply budget.

A Model Context Protocol server that wraps AutoIt functionality, enabling LLMs to automate Windows desktop tasks including mouse/keyboard operations, window management, and UI control interactions.

Enables AI assistants to discover and interact with local Power BI Desktop instances, including inspecting table/column schema and executing DAX queries.

Validates AI-generated Python: syntax, lint, security scan and deterministic repair.

An enhanced sequential thinking tool optimized for programming tasks that helps break down complex coding problems into structured, self-auditing thought steps with branching and revision capabilities.

.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.

MCP server for GitHub code retrieval and reuse, using SQLite+FTS5 indexing and search history to enable search-first, requirements-refined code search from GitHub repositories.