"Memory" matching MCP servers:

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Enables deterministic behavioral regression review of pull-request diffs by checking changed code against approved incident-derived contracts. It exposes read-only tools to assess diffs and pull requests, list and fetch contracts, and report outcomes over stdio without mutating repositories.

Enables users to list and inspect household memory-conflict tasks, score answers, run evaluations, and retrieve provenance data through MCP tools.

Enables Playwright QA automation with a custom Memory MCP that provides tiered retention and mortgage compliance audit, allowing AI agents to remember flakiness history and journey maps while adhering to data privacy and audit requirements.

Enables an agent to build and reuse a persistent library of tested scripts, listing and running saved helpers and saving new ones only after their tests pass.

MCP server exposing a "run" tool that benchmarks agent-memory backends and returns a reproducible JSON report.

Provides an in-memory notebook interface with tools to create, retrieve, list, update, and delete notes, designed to test agent behavior through realistic MCP tool interactions.

Runs SQL statements in memory against real PostgreSQL 18 and SQLite 3.49 engines after loading your schema and sample rows, returning each statement's own verdict: errors with line, column, and hints, constraint violations, or the resulting rows. It also compares both dialects to expose portability differences, all with no database server, network, or API key.

Enables building and evaluating shopping/support agents against a deterministic synthetic retail store with in-memory fixtures. Provides tools, resources, and prompts for product search, cart and order flows, inventory, and policy retrieval over stdio or Streamable HTTP.

Provides tools to test regex patterns for correctness, performance (ReDoS), and memory usage, and suggests safe rewrites. Enables LLMs to iterate on regex generation with verifiable feedback.

Enables any MCP client to debug programs through the Debug Adapter Protocol, supporting launch/attach, breakpoints, stepping, variable inspection, evaluation, and memory operations via a single debug tool.

An AppSec-focused MCP server that performs static analysis scans on C/C++ source code for memory-safety vulnerabilities and parses compiled PE/ELF binary headers locally to audit active defensive compiler mitigations (ASLR, DEP/NX, PIE).

A comprehensive security testing MCP server providing 51 tools for penetration testing, network forensics, memory analysis, and vulnerability assessment. It enables automated security audits and technical investigations across web applications, cloud environments, and network captures.

Enables programmatic control of the mGBA emulator for Game Boy, Game Boy Color, and Game Boy Advance games, including screenshot capture, memory reading, sprite data dumping, and custom Lua script execution for automated testing and game analysis.

Provides an in-memory mock commerce backend for shopping agents, enabling product search, order creation, simulated payment, automatic shipping/delivery progression, and refund workflows. It lets developers test full shopping-agent lifecycles deterministically without real products, credentials, or funds.

An MCP server based on Puppeteer and Chrome DevTools Protocol for advanced browser debugging, performance analysis, and memory detection. It enables users to inspect DOM elements, monitor console errors, capture screenshots, and perform heap snapshot analysis through persistent browser connections.

Provides deterministic application truth for Hugomemo Android QA, including server sessions, queue rounds, attempt details, skill ratings, memory score, entitlement, and usage, while leaving emulator interaction to a separate Android MCP.

Browser automation MCP server with persistent memory for AI assistants, enabling automated web testing and workflow replay with self-healing selectors.

Enables controlling and inspecting a running Dolphin emulator through its Debug Adapter Protocol, with persistent connections, task-oriented tools, and a raw request escape hatch for execution, breakpoints, stack/variables, memory, disassembly, sources, watches, scans, and code injection.

Enables AI assistants to evaluate task complexity, verify package installation safety, and log complex reasoning processes. Provides structured assessment of multi-step tasks and environment validation for safer code execution workflows.

A Windows-focused MCP server for controlling and debugging PCSX2 via GDB, offering emulator control, memory inspection, debugger operations, savestates, cheats, screenshots, process management, and log access.

Provides comprehensive debugging capabilities for Node.js and TypeScript applications with 25+ specialized tools, including breakpoint management, variable inspection, hang detection, CPU/memory profiling, and test framework integration.

Local MCP server for Android and iOS mobile automation and performance telemetry, enabling device control (screenshot, tap, swipe, input, app launch) and metric collection (CPU, memory, launch time) via ADB, simctl, and WebDriverAgent with SQLite session history.

Enables headless debugging of Windows executables from Linux/macOS hosts by orchestrating winedbg's gdbserver and a GDB client, exposing 19 tools for launch, attach, breakpoints, stepping, register/memory access, and session lifecycle.

Enables an AI agent to inspect live browser scene graphs, materials, shaders, lights, textures, animation, performance and memory, preview changes without touching project code, and convert the approved ones into vanilla or React Three Fiber source. It also provides website audits, smooth video frame capture, and Playwright/Puppeteer helpers.

Enables AI agents to store and recall persistent local memory across restarts and to run offline checks on generated text for arithmetic, date, percentage, URL, and absolute-claim errors, with optional multi-model consensus cross-checking.

Enables AI agents to inspect and live-edit 3D browser scenes — objects, materials, shaders, lights, textures, animation, performance and memory — and to turn previewed tweaks into ready-to-paste React Three Fiber or vanilla code. It also adds website audits, virtualized 60 fps frame capture for video, and Playwright/Puppeteer helpers, with no changes required to the user's project.

Enables AI agents to inspect and edit Three.js scenes, materials, shaders, lights, textures, animation, performance, and memory in real time, with live previews convertible into vanilla Three.js or React Three Fiber code. Also supports website audits, video frame capture, and Playwright/Puppeteer workflows.

Enables AI agents to inspect and live-edit running Three.js or React Three Fiber scenes in the browser, covering objects, materials, shaders, textures, lights, animation, performance and memory without modifying the project. Previewed changes can be converted into ready-to-paste vanilla Three.js or React Three Fiber code, and it also supports website audits, video frame capture and Playwright helpers.

Enables AI agents to inspect live Three.js and React Three Fiber scenes, try material, shader, light and camera changes in the browser without touching project files, and then write the approved changes back into source code. It also covers performance and memory analysis, website audits, video frame capture, and Playwright/Puppeteer test helpers through 69 tools.