"How to compare the master branch with a feature branch using Cursor" matching MCP servers:

Enables git-branch-style A/B experimentation for long-running tasks, allowing users to create, compare, promote, discard, or roll back parallel conversation branches via MCP tools.

Read-only MCP server exposing Git branch diff sessions, filtered file lists, patches, and commit metadata from the Branch Diff Explorer VS Code extension to local AI clients.

Enables AI agents to generate and retrieve a contextual document for a git branch, summarizing repository state, changes, and freshness, so they can understand the branch without scanning the entire codebase.

Enables Cursor AI to read and modify Figma designs programmatically via the Model Context Protocol.

Enables agents to find the gross salary in another location that leaves the same after-tax money once local living costs are covered, using built-in county budgets and place data. It also supports looking up locations, generating research prompts, and saving or contributing sourced location entries.

An MCP server that measures how faithfully one UI reproduces another, returning a score and actionable findings for improvement.

Enables unified administrative control over Cloudflare, Porkbun, Docker, Proxmox VE, Nginx Proxy Manager/NPMPlus, Uptime Kuma, Authentik, and Coolify. Exposes service discovery and action execution through three MCP tools with roughly 150 cataloged operations for managing DNS, containers, VMs, proxies, monitors, users, and related infrastructure.

Enables pixel-perfect image comparison and visual regression testing via tools to compare local images, screenshots, and URLs with detailed diff statistics.

Enables MCP clients to run Cursor CLI agent prompts with any model the installed CLI offers, continue existing sessions, and list available models and sessions. Adds guarded execution with concurrency limits, timeouts, cancellation, and operator-gated auto-approval so multiple models can be run in parallel.

mcp-test-runner is an MCP server that lets your AI client (Claude / Cursor / Codex / Gemini) drive your entire QA loop end-to-end: * Run tests across pytest / Jest / Cypress / Go / Maestro — single MCP surface, one env var to switch * Analyze a URL (Web DOM probe) or a live mobile screen (Maestro hierarchy) to extract testable modules + candidate cases * Generate runna

Enables Claude to offload bulk reading, first-draft writing, and mechanical edits to a local or OpenAI-compatible model, with code-enforced verification, staged patches, project checks, and token budgets to save tokens and cost.

A local knowledge graph MCP server that provides AI agents with permanent, structured memory about codebases, enabling semantic search, blast radius analysis, and convention enforcement.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

An MCP server that converts Markdown files containing Mermaid diagrams into PDF documents by rendering diagrams as SVG images. It provides a specialized tool to automate document conversion while ensuring all visual charts are correctly embedded in the final output.

Provides structured external memory for AI assistants, enabling persistent context, branch notes, tacit knowledge, and checklists to overcome AI memory loss and context confusion.

Enables AI harnesses to maintain a persistent memory layer backed by a local SQLite file, providing MCP tools to add, search, deprecate, and synchronize facts without deleting history.

Enables Cursor AI to read and modify Figma designs via the Model Context Protocol, allowing programmatic control over documents, components, styles, and more.

Enables Cursor and other MCP-compatible agents to control a Stack-chan robot companion, giving the AI vision, hearing, speech, movement, facial expressions, and environmental sensing.

Enables multi-agent code review and iterative improvement loop using different LLM backends, with deterministic scoring and audit trail.

A local MCP server that controls two Codex CLI agent instances via tmux, enabling parallel agent operations with lifecycle management, status classification, and secure path handling.