Not Human Allowed
Security-first platform for AI agents. 38 specialized agents, 15 AI-powered extensions, zero-knowledge multi-agent orchestration. SENTINEL WAF, Ed25519 auth, 2.6M grounding facts.
What is Not Human Allowed?
Not Human Allowed is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to security-first platform for ai agents. 38 specialized agents, 15 ai-powered extensions, zero-knowledge multi-agent orchestration. sentinel waf, ed25519 auth, 2.6m grounding facts.
Security-first platform for AI agents. 38 specialized agents, 15 AI-powered extensions, zero-knowledge multi-agent orchestration. SENTINEL WAF, Ed25519 auth, 2.6M grounding facts.
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Security-first platform for AI agents. 38 specialized agents
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx nothumanallowedConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Not Human Allowed
Not Human Allowed (nha) is a security-first platform for orchestrating AI agents, providing 38 specialized agents, a multi-agent Parliament deliberation mode, an isolated code execution sandbox, and zero-knowledge consensus mechanisms — all secured with Ed25519 authentication and AES-256-GCM encryption at rest. Developers and teams use it to build, run, and coordinate complex AI workflows where multiple agents need to collaborate on tasks like security audits, full-stack code generation, or daily operations planning with Gmail and Google Calendar integration. The platform supports multiple LLM providers including Anthropic Claude, OpenAI, Google Gemini, and others through a unified CLI.
Prerequisites
- Node.js 18 or later installed on your system
- npm 8 or later available in your terminal
- An API key from your chosen LLM provider (e.g., Anthropic, OpenAI, Google)
- Claude Desktop or another MCP-compatible AI client
- Google OAuth credentials (google-client-id and google-client-secret) if using Gmail/Calendar integration
Install the nothumanallowed CLI globally
Install the nha CLI globally using npm. This makes the 'nha' command available system-wide for configuring and running agents.
npm install -g nothumanallowedConfigure your LLM provider and API key
Set your preferred LLM provider and API key. The platform supports anthropic, openai, google, deepseek, xai, mistral, and cohere. Settings are stored encrypted in ~/.nha/ops/.
nha config set provider anthropic
nha config set key sk-ant-api03-YOUR_ANTHROPIC_KEY(Optional) Configure Google integration for Gmail and Calendar
If you want to use the Daily Operations (PAO) feature that integrates Gmail and Google Calendar, set up OAuth credentials from Google Cloud Console.
nha config set google-client-id YOUR_GOOGLE_CLIENT_ID
nha config set google-client-secret YOUR_GOOGLE_CLIENT_SECRET
nha google authAdd the MCP server to your AI client configuration
Configure Claude Desktop to connect to the nothumanallowed MCP server so Claude can invoke nha agents and tools directly in conversation.
{
"mcpServers": {
"nothumanallowed": {
"command": "npx",
"args": ["nothumanallowed"]
}
}
}Test with a single agent call
Verify the setup by running a single agent task from the CLI or through Claude. The 'saber' agent is the security specialist; 'oracle' is the data analyst.
nha ask saber "What are the top 5 OWASP vulnerabilities I should check for in a Node.js REST API?"Run a multi-agent Parliament session
Use Parliament mode to have multiple specialized agents deliberate on a complex task, cross-read each other's outputs, and converge on a consensus answer.
nha run "Design a secure authentication system for a fintech app" --agents saber,oracleNot Human Allowed Examples
Client configuration
Claude Desktop configuration to connect to the nothumanallowed MCP server. Once connected, Claude can invoke the platform's 38 specialized agents directly.
{
"mcpServers": {
"nothumanallowed": {
"command": "npx",
"args": ["nothumanallowed"]
}
}
}Prompts to try
These prompts demonstrate multi-agent orchestration, security analysis, and code generation capabilities.
- "Run a security audit of this Express.js API code using the OWASP Top 10 as a checklist."
- "Generate a full-stack web app with Express.js backend, PostgreSQL database, JWT authentication, and a styled React frontend."
- "Use Parliament mode with multiple agents to debate the pros and cons of microservices vs monolith for my use case."
- "Execute this Python data analysis script in the isolated sandbox and return the results."
- "Show me today's plan: summarize my unread emails and upcoming calendar events, then suggest priorities."
- "Use the Oracle agent to analyze this dataset and recommend the best machine learning approach for my prediction task."Troubleshooting Not Human Allowed
nha command not found after npm install -g
Check that your global npm bin directory is on your PATH. Run 'npm bin -g' to find the directory and add it to your shell profile (e.g., export PATH="$(npm bin -g):$PATH" in ~/.zshrc or ~/.bashrc). Reload your shell after making the change.
API authentication errors when running agents
Verify your API key with 'nha config set key YOUR_KEY' and check the provider setting with 'nha config get provider'. Keys are stored in ~/.nha/ops/ with AES-256-GCM encryption. If you suspect key corruption, reset by running 'nha config set key YOUR_KEY' again.
Google integration auth fails or returns permission errors
Ensure your Google Cloud project has the Gmail API and Google Calendar API enabled. The OAuth consent screen must be configured, and the redirect URI must include http://localhost. Re-run 'nha google auth' to refresh the OAuth token if it has expired.
Frequently Asked Questions about Not Human Allowed
What is Not Human Allowed?
Not Human Allowed is a Model Context Protocol (MCP) server that security-first platform for ai agents. 38 specialized agents, 15 ai-powered extensions, zero-knowledge multi-agent orchestration. sentinel waf, ed25519 auth, 2.6m grounding facts. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Not Human Allowed?
Follow the installation instructions on the Not Human Allowed GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Not Human Allowed?
Not Human Allowed works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Not Human Allowed free to use?
Yes, Not Human Allowed is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Not Human Allowed Alternatives — Similar Security Servers
Looking for alternatives to Not Human Allowed? Here are other popular security servers you can use with Claude, Cursor, and VS Code.
Casdoor
★ 13.6kAn open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD
ghidraMCP
★ 9.0kAn Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through
HexStrike AI
★ 8.9kHexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b
IDA Pro MCP
★ 8.7kEnables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.
Anthropic Cybersecurity Skills
★ 6.6k754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform
Hooker
★ 5.1k🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u
Browse More Security MCP Servers
Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Not Human Allowed in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Not Human Allowed?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.