"How to use Google Search" matching MCP servers:

Provides AI assistants with token-efficient access to Google Play Android Vitals, enabling them to diagnose ANRs, track crashes, analyze startup performance, and compare app versions for release optimizations.

Enables AI assistants to query the Google Play Developer Reporting API for Android production stability data, including crash and ANR issue clusters, de-obfuscated stack traces, release track discovery, startup and crash metric trends, version-to-version comparisons, and anomaly alerts. It also provides guided prompts for incident triage, baseline profile verification, and weekly stability reporting with built-in token compression and caching.

Reproduces a race condition in mcp-use dev where tool results are dropped when the handler completes after the widget iframe loads.

Launches multiple Browser-Use agents to automatically test websites for UI bugs, broken links, accessibility issues, and other technical problems on both live and localhost sites.

Enables agents to discover, search, compare, and inspect tested MCP tools by problem or keyword, with certification verdicts, scorecard summaries, certified scope, and explicit not-tested details.

MCP server for measuring web performance with Google PageSpeed Insights, providing median scores with uncertainty and real-user data. It offers tools for scores, diagnostics, and comparisons to identify regressions.

Enables AI assistants to run code in 24 programming languages on HackerEarth's sandboxed servers and read the printed output or errors, without installing local toolchains. It also lists supported languages with exact identifiers for use when submitting code.

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

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.

Enables developers to diagnose why FSE 2.0 CDA2 documents are rejected by validating locally, explaining schematron/XSD errors, looking up code systems, and generating synthetic sample documents.

A local-first MCP server that scores your codebase's Build Readiness by reading code and running tests on your machine, outputting a diligence-grade score and risk register without uploading your source.

MCP server for semi-manual QA test execution on real Smart TVs (Tizen/webOS) and local Chrome via Chrome DevTools Protocol, enabling remote control, state inspection, and profiling.

A stdio MCP server that audits other MCP servers over the live protocol. It connects to any MCP target (stdio or HTTP), lints every tool's schema for agent-usability, then actually calls the tools with deliberately broken inputs to see how the server handles them, and returns a 0–100 conformance score with a per-dimension breakdown rendered as Markdown.

A stdio MCP server providing AI agents with a stable tool interface to read and write TCM test cases through REST, including search, CRUD operations, and a dry-run-to-commit safety flow.

Enables testing how different MCP clients handle tool results containing both content and structuredContent, including outputSchema enforcement and mismatch scenarios.

The pixel-diff verifier for Figma-to-code: converts a frame to HTML, React, Next.js or Tailwind with design tokens, then renders it and pixel-diffs it against Figma until it converges. Also verifies your own running app.

Browser control for Claude Code, on Firefox.

Runs a regular expression on real engines — JavaScript (V8), Python (CPython re), PCRE2 and RE2 — reporting each engine's own compile errors with positions, every match with its groups and named groups, replacement results, and where the engines disagree. It also detects catastrophic backtracking (ReDoS), naming the at-risk part of the pattern, generating an attack string, and timing how long each engine actually takes on it.

Lets an MCP client query SQLite databases through validated, forced read-only, row-capped, time-limited and logged operations, so AI agents can explore data without risking writes or runaway queries. It also ships an eval harness that measures how accurately a model answers benchmark questions via text-to-SQL through the server.

Enables AI assistants to interact with TrafficMorph for load-testing and CI-failure triage, including run management, profile lifecycle, and domain verification through natural language.

Runtime access for AI coding agents to observe and control Android and iOS apps.

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.

Enables auditing any public website, returning a scored plain-English report that flags issues costing customers, covering speed, phone experience, search visibility, contact options, writing quality, and modernity.

A local, stdio-only Model Context Protocol server that lets coding agents inspect, control, and test Apple iOS Simulators and Google Android Emulators. It exposes 29 typed tools for device lifecycle, app management, UI automation, screenshots, logs, permissions, location, and platform-specific test conditions.

Enables AI agents to inspect Shadow Monitor capture files locally, with tools to load bundles, find errors, search network requests, and replay user actions.

Free, rules-based checks for e-commerce product pages: AI shopping readiness (structured data, reviews, return and shipping terms, GTINs, AI crawler access), Google Merchant Center compliance, store SEO audit and Shopify checkout deadlines. No AI calls, nothing stored.

Enables read-only accessibility snapshots of active third-party iOS keyboard extensions in Simulator, returning JSON with absolute logical coordinates for use by automation tools.

Enables AI agents to formally verify constant-time, masking, and patch completeness properties of Verilog hardware designs, providing concrete leakage signals and next-step guidance.

Enables recording how React components render in headless Chrome and explains the main performance problem in a card inside Claude.

Enables LLMs and agents to check their own work by calling tools instead of trusting assertions, covering symbolic math identities, sandboxed Python execution, JSON-Schema validation, dimensional analysis, and regex testing. Runs over stdio or streamable HTTP for use in Claude Desktop and remote gateway deployments.

Real-time Core Web Vitals (LCP) telemetry, DOM bloat analysis, and AI search crawler (GEO) readiness audits for AI coding assistants.

Enables AI agents to run deterministic data-center engineering calculations and commissioning audits, including liquid-cooling hydraulics, pipe friction and flow checks, corrosion severity classification, protocol search, and defect-code lookup.

Enables migration of test automation projects from WebDriverIO to Playwright using AST-based transformations. Provides tools for analyzing tests, converting syntax, refactoring to Page Object Model, and generating migration reports.

Build, sign, and publish iOS and Android apps through AI agents. Integrates Codemagic CI/CD, App Store Connect, and Google Play in one server.

An MCP server that enables AI agents to drive Zephyr for Jira (Server/Data Center) test management via ZAPI. It exposes operations for test cycles, folders, executions, test steps, step results, and ZQL search over stdio for use with any MCP client.

Model Context Protocol (MCP) server for App Store Optimization. Score your App Store / Google Play listing metadata, check character limits, and clean up the iOS keyword field — right inside Claude, Cursor, or any MCP client.

Enables AI agents to query synthetic packaged-coffee pricing data for elasticity estimates, price-change simulations, guardrail checks, price-ladder validation, and competitor positioning while logging read-only tool calls. It also includes evaluation tooling for grading whether agents use those pricing tools correctly and ground their answers in tool outputs.

Enables users to browse, retrieve, and search practical guide topics and ready-made snippets for configuring Delphi projects, DUnitX runners, CodeCoverage CLI invocations, and CI pipelines so coverage works correctly.

MCP server enabling AI agents to create, update, search, assign, and complete tasks on TaskLogger.io via the TaskLogger REST API, with secure local credential management and token persistence.

Generate, extend and verify MCP servers in Go.