RamiBot
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team skill pipeline, MCP tool orchestration, Docker terminal access, Tor proxy management, and an auto-integrated Kali-based tool server
What is RamiBot?
RamiBot is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ramibot v3.8.0 is a local-first ai security operations platform integrating multi-llm support, a dynamic red/blue team skill pipeline, mcp tool orchestration, docker terminal access, tor proxy managem...
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team skill pipeline, MCP tool orchestration, Docker terminal access, Tor proxy management, and an auto-integrated Kali-based tool server
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- RamiBot v3.8.0 is a local-first AI security operations platf
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ramibotConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use RamiBot
RamiBot is a local-first AI security operations platform that combines multi-LLM support, a structured red and blue team skill pipeline, Docker-integrated terminal access, and a built-in Kali Linux MCP server with 45+ pentesting tools. It connects AI reasoning (via OpenAI, Anthropic, OpenRouter, LM Studio, or Ollama) to real security tool execution inside controlled containerized environments, with a human-in-the-loop tool approval gate that pauses before every MCP tool call. Security professionals and pentesters can use it to run structured recon-to-reporting pipelines, correlate CVE intelligence with detected services, manage Tor proxy routing, and export one-click PDF security reports.
Prerequisites
- Python 3.9 or higher installed
- Node.js 18 or higher and npm installed
- Docker Desktop installed and running (required for Kali Linux MCP server and Docker terminal features)
- At least one LLM provider API key: OpenAI API key, Anthropic API key, or a local Ollama/LM Studio instance
- Git to clone the repository
Clone the repository
Clone the RamiBot repository to your local machine.
git clone https://github.com/RamiBotAI/ramibot.git
cd ramibotRun the one-command installer
The install script checks all prerequisites, installs missing ones where possible, sets up the Python virtual environment, installs npm dependencies, builds the Kali Docker image, and copies the example settings file.
# Linux / macOS
bash install.sh
# Windows
install.batConfigure your API keys
Edit backend/settings.json (created by the installer from settings.example.json) to add your LLM provider API keys. Set at least one of OPENAI_API_KEY or ANTHROPIC_API_KEY.
# backend/settings.json (partial — add your keys)
{
"llm": {
"provider": "anthropic",
"api_key": "your-anthropic-api-key"
}
}Start RamiBot
Use the start script to launch both the backend and frontend. The app opens at http://localhost:5173 after a few seconds.
# Linux / macOS
bash start.sh
# Windows
start.batWait for the Kali Docker image to build on first launch
On the very first start, RamiBot builds the rami-kali Docker image in the background. This takes a few minutes depending on your connection speed. Subsequent launches are instant.
RamiBot Examples
Client configuration
RamiBot runs as a standalone web application at http://localhost:5173. It manages its own MCP tool orchestration internally. The following shows the backend service configuration for reference.
{
"mcpServers": {
"ramibot": {
"command": "python",
"args": ["-m", "uvicorn", "main:app", "--port", "8000"],
"env": {
"ANTHROPIC_API_KEY": "your-anthropic-api-key"
}
}
}
}Prompts to try
Use these prompts inside the RamiBot chat interface for security operations tasks.
- "Run a port scan on 192.168.1.0/24 and identify open services"
- "After the port scan, correlate detected services with known CVEs"
- "Start a Recon skill pipeline against target 10.0.0.5"
- "Enable Tor proxy routing and confirm my exit IP has changed"
- "Generate a PDF security report summarizing all findings from this session"Troubleshooting RamiBot
Docker image build fails or Docker is not found
Ensure Docker Desktop is installed and running before running install.sh. The installer checks for Docker and aborts if it is not found. On Linux, also ensure your user is in the docker group (sudo usermod -aG docker $USER) and restart the session.
LLM API calls fail with authentication errors
Open backend/settings.json and verify your API key is correctly entered. For Anthropic, the key starts with sk-ant-. For OpenAI, it starts with sk-. Restart the backend after editing settings.json.
Frontend does not load at http://localhost:5173
Check that both the backend (port 8000) and frontend (port 5173) processes are running. Run them manually in two separate terminals: cd backend && python -m uvicorn main:app --port 8000 and cd frontend && npm run dev.
Frequently Asked Questions about RamiBot
What is RamiBot?
RamiBot is a Model Context Protocol (MCP) server that ramibot v3.8.0 is a local-first ai security operations platform integrating multi-llm support, a dynamic red/blue team skill pipeline, mcp tool orchestration, docker terminal access, tor proxy management, and an auto-integrated kali-based tool server It connects AI assistants to external tools and data sources through a standardized interface.
How do I install RamiBot?
Follow the installation instructions on the RamiBot GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with RamiBot?
RamiBot works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is RamiBot free to use?
Yes, RamiBot is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
RamiBot Alternatives — Similar Security Servers
Looking for alternatives to RamiBot? 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 RamiBot 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 RamiBot?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.