"How to find and troubleshoot a memory leak in software" matching MCP servers:

Detects whether sensitive data like emails, SSNs, and phone numbers survive in supposedly redacted PDFs, running entirely locally via WebAssembly.

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

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.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

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.

Provides a hand-written MCP server integrated with a LangGraph agent to benchmark multiple agent topologies and measure their failure rates.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Enables turning requirements documents into RFCs, functional test scenarios, and a traceability matrix, with tools to parse, diff, and verify coverage.

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.

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.

Enables agents to turn a plain-language description of a device into a complete, validated build package — parts list, 3D-printable parts, wiring, firmware code, picture assembly guide, and tests — that anyone can assemble without electronics experience.

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-first A/B testing server that enables agents to manage experiments (create, update traffic splits, read results, apply winning variants) from tools like Claude Code, with self-hosted Cloudflare backend.

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 reproducible evaluation of AI coding agents by exposing repository inspection, code editing, test running, and deterministic verification through MCP tools.

Provides a testable gateway path for running a local MCP-style server in hosted-like conditions, with tenant-isolated reads, approval-denied writes, deterministic failures, and smoke-test verification.

Enables LLMs to interact directly with generated REST services by discovering and invoking CRUD tools and reading exposed resources for list and get-by-id data.

Gives your AI the super power of traveling back in time to find what went wrong and fix the bug timeline.

Enables AI assistants to interact with iOS Simulators and Android Emulators, allowing autonomous app development, UI interaction, profiling, and debugging through natural language.

Free JSON Schema validation, JSON to TypeScript, CSV to JSON, JSON repair and JSON to CSV for AI agents. Hosted MCP plus local STDIO. Connect once with a scoped key; enforce tool allowlists and quotas, inspect request IDs. Runnable repair → validate → CSV workflow. Bounded OpenAPI and webhook checks. No LLM calls or payments. Setup: invokeport.com/agents.

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.

Validates .mcp.json and claude_desktop_config files to catch duplicate server names, missing binaries, invalid environment variables, and unreachable endpoints. Reports each problem along with how to fix it, so silently failing MCP servers can be diagnosed and repaired.

Maps Electron app IPC handlers to MCP tools and provides 33 built-in CDP tools for DOM automation, screenshots, interaction, and debugging, enabling Claude Code to directly control your Electron app.

Enables MCP clients to retrieve lab performance scores and field Core Web Vitals data for web pages via Google APIs.

Enables users to run synthetic support-agent evaluations, preserve and inspect traces, score results deterministically, inject failures, and enforce release review gates through MCP tools, resources, and prompts.

Generates a pytest suite from acceptance criteria withheld from the coding agent, so the tests can disagree with the code; qikly_run never returns the criteria. The CLI also scores an existing suite by planting faults, and ships as an agent Skill (qikly --install-skill). Runs locally (uvx --from "qikly[mcp]" qikly-mcp): your code and API key stay on your machine.

Enables AI coding assistants to scan an iOS, Android, Flutter, React Native or Expo project for App Store and Google Play rejection risks, returning deterministic findings that cite the guideline section, link to the official Apple or Google page and explain how to fix each problem. Nothing leaves the machine and no AI is used in the checks.