"Local MCP servers for self-hosted AI assistants" matching MCP servers:

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.

Audit a web page for SEO and technical issues with Marlo, the open-source AI CMO. Read-only: returns the top findings with evidence, why each matters, and a concrete fix.

Guarded, profile-driven Charles Proxy automation for macOS and Android testing. Uses immutable TOML profiles and explicit plan/apply confirmation.

Spring AI Playground is a self-hosted web UI platform for building low-code tools and dynamically exposing them via built-in MCP server for AI agents.

Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.

Checks a site for AI crawlers: which of 11 AI crawlers its robots.txt lets in, whether its llms.txt follows llmstxt.org, and what its home page says without scripts. Findings with evidence; no scores, no model calls, no telemetry.

A local MCP server that connects Claude Desktop, Claude Code, and Claude Chat to your Azure DevOps organization, enabling querying work items, reviewing pull requests, triggering pipelines, searching code, managing test plans, and updating wikis using plain language.

Enables measuring DOM elements and capturing screenshots in a real local Chrome browser over the DevTools Protocol, with in-page login so httpOnly cookies apply and overlay-masking before capture. It removes common Chrome automation traps such as sandbox kills, WebSocket origin rejection, and Retina pixel scaling, with no npm or Python dependencies beyond the MCP SDK.

A licensed, locally run Playwright E2E testing MCP server for Claude Desktop and Cursor. It lets AI coding agents inspect semantic accessibility structure, validate role-based browser flows with explicit assertions, and generate reusable Playwright tests.

MCP server for measuring, tracking, scoring, and improving AI agent reliability with tools for recording interactions, scoring reliability, analyzing failures, recommending improvements, generating audit reports, and checking MCP health.

Enables agents and teams to manage versioned delivery work items, role-tagged handoffs, revision- and source-bound evidence, QA gate evaluation, and release-owner attestations through MCP tools.

Enables scanning text for policy and safety issues, generating test suite outlines, and checking the configuration/health of the evaluation setup.

MCP server for AI-powered QA analysis. It enables analyzing test failures, identifying root causes, suggesting fixes, classifying defects, detecting flaky tests, and generating test cases and bug reports.

An MCP server for validating AI-generated code through automated browser testing, evidence collection, and intelligent diagnostics.

Enables AI assistants to write and run mobile UI tests on Android and iOS simulators via natural language, supporting native and WebView apps without Appium.

A multi-task MCP server for AI code optimization and testing that integrates with VSCode/Cursor, CLI tools, and autonomous agents. It provides tools for running tests, generating code improvements, and managing objectives across different environments.

Enables AI assistants to answer QA questions in a single call, covering run reports, failure grouping by root cause, flaky versus regressed test detection, and coverage gaps. Also exposes raw TestRail API access when a question needs it.

Accessibility AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

A multi-language testing automation server that enables AI assistants to discover, plan, and execute tests across six major programming languages. It provides comprehensive tools for repository scanning, automated test execution, and detailed coverage reporting.

An MCP server that generates, runs, and triages tests by introspecting Python modules or web pages, using structured LLM outputs for scenario generation and failure analysis.

A lightweight MCP server for security reviews that injects security requirements before code generation, scans dependencies for CVEs, and verifies generated code without disrupting workflow.

A local MCP server that lets Claude Code and Codex delegate repository exploration and test proposals to a remote LM Studio model, while enforcing security boundaries by keeping all repository access read-only and never applying patches or running commands remotely.

An MCP server for validating JSON against schemas, checking email deliverability, verifying URLs, assessing data quality, and validating API responses using RFC-compliant checks and heuristic analysis.

Enables autonomous agents to automatically repair and guard tool-call schemas through deterministic AST analysis and parameter projection validation, ensuring reliable, schema-compliant interactions in MCP-compatible environments.

Enables AI assistants to interact with the Scorecard REST API for exploring endpoints, making test requests, and integrating the SDK into applications.

Broccoli turns "the agent reads a stack trace and guesses" into "the agent drives the real debugger": it sets breakpoints, steps, inspects live variables over the Debug Adapter Protocol, and proposes a fix you approve in a diff — never applied silently.

AI-powered E2E testing MCP server. Point at a URL — AI generates test scenarios, runs Playwright tests, and self-heals failures automatically. Works on Canvas and Flutter Web apps.

Enables automated QA testing by running a pipeline of AI agents that generate test scenarios, architect test layers, write Playwright tests, and review code, all grounded in feature requirements and API contracts.

Enables authenticated clients to retrieve problem information and optimization hints, manage source revisions and custom data, and submit or query Ascend C/NPU evaluation tasks.

Enables evidence-first release readiness assessment by running or accepting build, API, browser, visual, performance, and security evidence, then returning SHIP, REVIEW, or HOLD recommendations with clustered regressions.