"Villager 0.2.1rc1 Framework MCP Auto Penetration Testing" matching MCP servers:

Hosted email for AI agents. Connect Gmail, Outlook / Microsoft 365 or any IMAP mailbox to Claude, ChatGPT, Cursor and other MCP clients, then read, search, send, organize, draft, schedule and auto-triage mail. Email is fetched live and never stored. Free for 1 inbox.

Self-hostable, markdown-native team wiki with a built-in MCP server: agents search, read, and write your wiki pages (ranked Postgres full-text + semantic search, backlink traversal). Plus Atlas, which auto-generates a cited, coverage-checked wiki from your git repos and Jira.

This MCP server enables AI agents to perform exploratory UI testing of live web apps by providing a structured view of page elements, deterministic correctness oracles, enforced read-only or opt-in write policies, persistent cross-run memory, and gap-checked coverage reports.

Enables AI assistants to automate mobile app testing and development for iOS and Android through natural language interactions. Supports intelligent element identification, session management, automated test generation, and comprehensive device interactions including clicks, swipes, screenshots, and app management.

Enables LLMs like Claude to navigate the web through Puppeteer-based tools and Steel. Based on the Web Voyager framework, it provides tools for all the standard web actions click clicking/scrolling/typing/etc and taking screenshots.

Enables comprehensive Windows system management through Claude Desktop, including PowerShell/CMD execution, file operations, archive handling, Git tools, network testing, and system monitoring. Provides a complete toolkit for Windows automation and administration tasks.

It exposes business-logic services as MCP tools over streamable HTTP (stdio also supported), auto-registering each service so agents can invoke it through the same Pydantic contracts used by the bundled CLI and HTTP API. It also supports OAuth, per-call pricing, and optional UI enhancers for elicitation, image output, and dashboards.

Records and visualizes evidence from a coding agent's own testing tools in a private local workspace, with live activity, domain charts, screenshot maps, findings, reproduction steps, human priorities, and persisted testing preferences. Runs 54 bundled CARBON command workflows over local stdio and serves a loopback-only visual workspace with strict evidence and permission gates.