MCP for Security (Python)
一个为主流渗透测试工具打造的MCP服务器集合。 | A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Integrate security testing and penetration testing into AI workflows.
What is MCP for Security (Python)?
MCP for Security (Python) is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 一个为主流渗透测试工具打造的mcp服务器集合。 | a collection of model context protocol servers for popular security tools like sqlmap, ffuf, nmap, masscan and more. integrate security testing and penetration testing into a...
一个为主流渗透测试工具打造的MCP服务器集合。 | A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Integrate security testing and penetration testing into AI workflows.
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 一个为主流渗透测试工具打造的MCP服务器集合。 | A collection of Model Context Prot
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-for-security-pythonConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP for Security (Python)
MCP for Security (Python) is a collection of MCP servers that wrap popular penetration testing and reconnaissance tools — including SQLMap, FFUF, NMAP, Masscan, Nuclei, Amass, and more — so AI models can invoke them through natural language. Each security tool gets its own server module, enabling AI-driven security workflows such as automated scanning, vulnerability discovery, and fuzzing without manual CLI interaction. The collection covers 20 tools spanning reconnaissance, scanning, fuzzing, exploitation, and mobile/cloud analysis.
Prerequisites
- Python 3.8 or higher installed
- FastMCP 2.0.0 or higher (pip install fastmcp>=2.0.0)
- The specific security tool binary installed and on PATH (e.g., nmap, sqlmap, ffuf)
- An MCP-compatible client such as Claude Desktop
- Root or sudo access may be required for some scanning tools (e.g., nmap, masscan)
Clone the repository
Clone the mcp-for-security-python repository and navigate into the tool directory you want to use.
git clone https://github.com/f1tz/mcp-for-security-python.git
cd mcp-for-security-pythonInstall FastMCP and dependencies
Install the FastMCP framework and then install per-tool dependencies from the tool's own requirements.txt.
pip install fastmcp>=2.0.0 aiohttp>=3.8.0
# Then for your chosen tool:
cd nmap-mcp && pip install -r requirements.txtVerify the target tool binary is available
Make sure the underlying security tool is installed and accessible from your PATH before starting the server.
which nmap # or: which sqlmap, which ffuf, which masscanStart the tool-specific MCP server
Launch the server for the chosen tool by passing the path to the binary. API-based tools also need the endpoint URL and API key.
# For binary-based tools:
python server.py /usr/bin/nmap
# For API-based tools (e.g., mobsf):
python server.py http://localhost:8000 your_api_keyConfigure your MCP client
Add the server entry to your claude_desktop_config.json. Repeat for each security tool you want to expose.
MCP for Security (Python) Examples
Client configuration
Example configuration exposing the nmap and sqlmap MCP servers to Claude Desktop. Adjust paths and tool binaries as needed.
{
"mcpServers": {
"nmap-mcp": {
"command": "python",
"args": ["/path/to/mcp-for-security-python/nmap-mcp/server.py", "/usr/bin/nmap"]
},
"sqlmap-mcp": {
"command": "python",
"args": ["/path/to/mcp-for-security-python/sqlmap-mcp/server.py", "/usr/bin/sqlmap"]
}
}
}Prompts to try
Sample prompts that drive the security tools via AI. Always ensure you have written authorisation before scanning any target.
- "Run an nmap service version scan against 192.168.1.0/24 and summarise open ports"
- "Use sqlmap to test https://testphp.vulnweb.com/artists.php?artist=1 for SQL injection"
- "Fuzz /api/FUZZ on http://target.local with ffuf using a common wordlist"
- "Perform a masscan on 10.0.0.1-10.0.0.255 for ports 80, 443, and 8080"Troubleshooting MCP for Security (Python)
Server crashes immediately with ModuleNotFoundError for fastmcp
Install FastMCP 2.x: pip install fastmcp>=2.0.0. The project requires the newer FastMCP API and will not work with older versions.
Tool binary not found error when starting the server
Pass the absolute path to the binary as the first argument to server.py (e.g., python server.py /usr/local/bin/nmap). Ensure the binary is executable and on your PATH.
Runtime errors or unexpected tool output
The project notes it has not been verified through manual real-machine testing and may contain defects from AI refactoring. Test each tool independently first and cross-check results against direct CLI invocation.
Frequently Asked Questions about MCP for Security (Python)
What is MCP for Security (Python)?
MCP for Security (Python) is a Model Context Protocol (MCP) server that 一个为主流渗透测试工具打造的mcp服务器集合。 | a collection of model context protocol servers for popular security tools like sqlmap, ffuf, nmap, masscan and more. integrate security testing and penetration testing into ai workflows. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP for Security (Python)?
Follow the installation instructions on the MCP for Security (Python) GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP for Security (Python)?
MCP for Security (Python) works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP for Security (Python) free to use?
Yes, MCP for Security (Python) is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP for Security (Python) Alternatives — Similar Security Servers
Looking for alternatives to MCP for Security (Python)? 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 MCP for Security (Python) 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 MCP for Security (Python)?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.