"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

Enables AI agents to inspect UI screen recordings as token-efficient image sheets with changed regions boxed, single-frame flicker flagged, and speech aligned to frames. Exposes watch_video and zoom_video tools so agents can pull dense keyframes across any time range or one sharp full-resolution frame, all processed locally.

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.

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.

Fact-checks and fixes AI outputs by catching hallucinations, repairing broken JSON, and correcting errors before they reach users, with tools for verification, validation, and correction.

Lets an assistant read recorded production AI agent runs — steps, model and tool calls with arguments, and outcomes — along with the findings of comparison runs that checked a prompt or model change against those recordings, and verify a signed evidence bundle offline with no account or network. It is strictly read-only: no tool starts a replay or comparison, so nothing can spend money or act without a person deciding.

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.

MCP server for remote debugging of Apps in Toss mini-apps, providing CDP relay and test runner capabilities.

MCP server for the Ghost Inspector API that lets agents inspect and manage end-to-end browser tests, offering read-only tools for inventory, module usage, and stale test analysis, plus opt-in guarded write operations.

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

Measures what MCP servers cost in context tokens: probes a URL or a local command now, measures a whole config file, and looks up the daily results for every server in the official MCP registry on mcpcost.ulehla.dev.

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.

Screen-reader navigation cost analyzer. Measures how hard it is for assistive-technology users to discover, reach, and operate interactive targets on the web.

Renders HTML in a headless browser and detects layout defects numerically, such as text overlaps, placeholder leftovers, and element overflow, without requiring baseline images.

MCP server for managing test cases, cycles, and results in Zephyr Scale on self-hosted Jira. Enables AI agents to create, search, update, and delete test artifacts through natural language.

Run the requests in a Postman collection folder and get structured, assertion-level results back straight from your AI assistant.

Enables AI coding agents to test and automate Android apps rendering UI in OpenGL/Vulkan/Metal surfaces via screenshot-based vision tools for tapping, swiping, long-pressing, and recording, without accessibility tree dependency.

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.

Detects tests that pass no matter what the code does, revealing vacuous tests that provide false confidence in coverage.

MCP server that lets AI agents rent a real UK phone number and receive SMS/OTP verification codes directly in agentic workflows.

Enables AI agents to perform software engineering tasks inside an isolated, deterministic sandbox—exploring repositories, reproducing failures, applying patches, running tests, and verifying solutions against hidden suites through MCP tools.

Enables AI agents to simulate network failures and test application resilience in Playwright browser sessions.

Enables AI agents to verify that every number, money amount, percentage, count, date and time in an AI-written Japanese summary or meeting minutes actually appears in the source text, normalizing kanji numerals, 万/億, full-width digits, Japanese era years, 午前/午後 times and 割/分 rates before comparison. Exposes a read-only check tool that reports each fact as supported, approximate, mismatched or unsupported, plus an extraction tool that lists the quantities in a text.

Enables Codex to inspect, test, and control Android emulators through adb with strict typed tools, returning screenshots as native MCP images and keeping physical devices and Gradle execution behind explicit opt-in policies.

Enables AI agents to run Jest/TypeScript tests in isolated workspaces for Test-Driven Development workflows.

Automatically scans project dependencies (npm, Composer) for security vulnerabilities using the OSV.dev database, providing real-time alerts and detailed remediation guidance directly in your IDE.