Roadrecon
🐍 🪟 🏠 MCP server for analyzing ROADrecon gather results from Azure tenant enumeration
What is Roadrecon?
Roadrecon is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍 🪟 🏠 mcp server for analyzing roadrecon gather results from azure tenant enumeration
🐍 🪟 🏠 MCP server for analyzing ROADrecon gather results from Azure tenant enumeration
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🐍 🪟 🏠 MCP server for analyzing ROADrecon gather results from
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx roadreconConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Roadrecon
The ROADrecon MCP Server is a Python-based MCP server that lets AI assistants analyze Azure tenant enumeration data collected by the ROADrecon tool. It connects to a running ROADrecon web instance and exposes tools for identifying privileged users, assessing MFA coverage, detecting stale accounts, analyzing conditional access policies, and auditing service principal credentials. Azure security engineers and red teamers use it to get rapid AI-assisted insights into an Azure tenant's security posture without manually querying the ROADrecon database.
Prerequisites
- Python 3.8 or higher with pip installed
- ROADrecon installed and a gather operation already completed (pip install roadrecon, then roadrecon gather)
- A running ROADrecon web instance accessible at a known URL (default: http://localhost:5000)
- An MCP-compatible client such as Claude Desktop or Claude Code
Clone the MCP server repository
Clone the roadrecon_mcp_server repository and enter the project directory.
git clone https://github.com/atomicchonk/roadrecon_mcp_server.git
cd roadrecon_mcp_serverInstall Python dependencies
Install the required Python packages from the requirements file.
pip install -r requirements.txtRun a ROADrecon gather on your target tenant
If you have not already gathered data, run roadrecon against your Azure tenant. This populates the local database that the MCP server will query.
roadrecon gather --username [email protected]
roadrecon gui # starts the web UI at http://localhost:5000Set the ROADRECON_URL environment variable
Point the MCP server at your ROADrecon web instance. If running on the default port you can skip this step.
export ROADRECON_URL=http://localhost:5000Configure your MCP client
Add the server to your MCP client configuration, pointing to the Python script and the correct interpreter.
Start an Azure security analysis
Ask your AI assistant to run one of the analysis tools such as find_privileged_users or analyze_mfa_status to get an immediate overview of your tenant's security posture.
Roadrecon Examples
Client configuration
Example claude_desktop_config.json for the ROADrecon MCP server. Adjust the python path and script path to match your environment.
{
"mcpServers": {
"roadrecon": {
"command": "python",
"args": ["/absolute/path/to/roadrecon_mcp_server/roadrecon_mcp_server.py"],
"env": {
"ROADRECON_URL": "http://localhost:5000"
}
}
}
}Prompts to try
Example prompts that exercise the ROADrecon analysis tools once the server is connected.
- "Find all privileged users in this Azure tenant and list their role assignments"
- "Analyze MFA status across all users and identify accounts without MFA enabled"
- "Identify stale accounts that have not logged in for more than 90 days"
- "Find all applications that have stored credentials or secrets and assess their risk"
- "Review the conditional access policies and flag any gaps that allow MFA bypass"
- "Analyze service principal credentials and flag any with long-lived secrets"Troubleshooting Roadrecon
Connection error: cannot reach ROADrecon at http://localhost:5000
Ensure the ROADrecon web GUI is running ('roadrecon gui' or 'roadrecon-gui'). If running on a different port, set ROADRECON_URL accordingly, e.g. ROADRECON_URL=http://localhost:8080.
Tools return empty results for users or groups
The ROADrecon database must be populated before the MCP server can query it. Run 'roadrecon gather' with valid Azure credentials first. Check that the gather completed successfully with 'roadrecon dump'.
Python import errors when starting the MCP server
Run 'pip install -r requirements.txt' again inside the roadrecon_mcp_server directory and confirm you are using Python 3.8+. If using a virtualenv, activate it before starting the server or before pointing the MCP client at the Python binary.
Frequently Asked Questions about Roadrecon
What is Roadrecon?
Roadrecon is a Model Context Protocol (MCP) server that 🐍 🪟 🏠 mcp server for analyzing roadrecon gather results from azure tenant enumeration It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Roadrecon?
Follow the installation instructions on the Roadrecon GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Roadrecon?
Roadrecon works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Roadrecon free to use?
Yes, Roadrecon is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Roadrecon Alternatives — Similar Security Servers
Looking for alternatives to Roadrecon? 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 Roadrecon 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 Roadrecon?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.