Security & Testing Servidores MCP

Package Version

Provides LLMs with the latest stable package versions for multiple package registries when coding.

VirusTotal

Query the VirusTotal API for comprehensive security analysis and relationship data.

Shodan

Query the Shodan API and CVEDB to gather network intelligence and security insights.

Ghidra

Enables AI assistants to connect to Ghidra for AI-assisted binary analysis via the Model Context Protocol (MCP).

MCPControl

Provides programmatic control over system operations including mouse, keyboard, window management, and screen capture functionality.

Sandbox

Executes code and configurations from Large Language Models (LLMs) in secure, isolated Docker containers.

HTTP OAuth

Provides a reference implementation for creating a remote MCP server that supports Streamable HTTP & SSE Transports, authorized with OAuth.

Test Client

Facilitates the development and testing of MCP servers by acting as both a server for Claude and a client for servers under test.

Deep Code Reasoning

Provides advanced code analysis and reasoning capabilities by orchestrating Google's Gemini AI and Claude Code for complex debugging and understanding distributed systems.

iPhone

Automates iPhone tasks, including app control, UI interactions, and screenshot capture, via a streamable HTTP server using Appium.

JavaSinkTracer

Audits Java source code for vulnerabilities using function-level taint analysis, providing security insights to AI assistants.

IDA Headless

Facilitates remote, concurrent IDA Pro binary analysis by orchestrating multiple headless IDA instances through the Model Context Protocol.

FlowLens

Empowers AI coding agents with full browser context to streamline debugging and regression testing workflows.

Multi-Agent Ralph Wiggum

Orchestrates multiple AI models through an 8-step workflow, delivering high-quality, validated code with token optimization and automatic context preservation.

Deterministic Agent Control Protocol

Provides a governance gateway for AI agents, ensuring every action is bounded, auditable, reversible, and explainable through a robust control plane.

Pare

Wraps popular developer tools with structured, token-efficient, schema-validated output for AI coding agents.

SkillLite

Provides a lightweight AI Agent Skills engine with a built-in native system-level sandbox, zero dependencies, and fully local execution.

Mockd

Provides a high-performance, multi-protocol mock server supporting HTTP, WebSocket, gRPC, MQTT, SSE, GraphQL, and SOAP from a single binary.

Firefox DevTools

Enables AI assistants to inspect, control, and automate the Firefox browser through the Remote Debugging Protocol, leveraging WebDriver BiDi.

Deep Code Reasoning

Leverages Google's Gemini AI and Claude Code for advanced, multi-model code analysis, reasoning, and debugging of complex systems.