"Kagi" matching MCP servers:

MCP server for the nagi-ledger audit ledger and guardrail toolkit, exposing tools to record and annotate AI agent actions, subagent dispatches, and known dead ends, plus query session reports and statistics.

A task-based AI orchestrator that bridges AI models (Gemini, Claude, OpenAI) with local environments, operating as an interactive CLI and an MCP server for structured autonomous development.

MCP server that runs offensive security testing tools (nmap, sqlmap, hydra, nuclei, etc.) inside an isolated Kali Linux Docker container, with allowlist, rate limiting, and audit logging.

It lets LLM clients drive a browser by specifying outcomes while a TypeSafe System One model chooses each action and Playwright executes it. It also provides tools for checking page state, selecting among options, snapshots, and direct actions.

Enables WebGPT to delegate durable coding-project tasks to a local Luna worker over MCP, managing sessions, tools, permissions, memory, and recovery while preserving at-most-once execution.

An advanced MCP server implementing a cognitive architecture through the GOTCHA framework and ATLAS process for sophisticated task management and reasoning. It provides persistent SQLite memory, lifecycle hooks, and a subagent system to enable complex, agentic AI workflows.

Enables AI agents to safely execute OSINT and reconnaissance tools from Kali Linux through a typed job API with bearer authentication, job validation, and allowlisted Docker execution.

Safe, reliable, and verifiable execution for the Model Context Protocol, enabling governed tasks with planning, capability approval, side-effect verification, and evidence receipts.

Integrates 193 Kali Linux security tools with AI for intelligent penetration testing, CTF solving, and vulnerability assessment through automated workflows and expert knowledge base.

Enables LLMs to execute Kali Linux security tools like nmap, sqlmap, and hydra in a secure, sandboxed environment. Provides both MCP and HTTP API interfaces for penetration testing and security assessment tasks.

A server that implements the Model Context Protocol (MCP) for orchestrating code reviews using a multi-agent system with Melchior, Balthasar, and Casper agents.

An advanced MCP server that provides stateful voice-controlled AGI capabilities with local STT, TTS, and intent detection. It enables users to execute tools, manage memory, and conduct research through natural multi-turn dialogue with low-latency performance tracking.

AI-powered autonomous penetration testing framework with 80+ professional security tools across reconnaissance, web application testing, exploitation, and forensics. Integrates with LM Studio for intelligent vulnerability assessment and automated security testing workflows.

An MCP server that routes tasks to the best AI models, aggregates responses with confidence scoring, and applies billionaire thinking frameworks for strategic decisions.