What does the server need to run?
Python 3.8+ and a running ROADRecon instance with the web GUI accessible. An MCP-compatible client (e.g., Claude Desktop) is required to use the server.
@atomicchonk
Basic information
Claude MCP server to perform analysis on ROADrecon data
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"roadrecon-mcp-server": {
"command": "python",
"args": [
"roadrecon_mcp_server.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
An MCP server that provides AI assistants like Claude with access to ROADRecon Azure AD data for security analysis. It acts as a bridge between an MCP-compatible client and a running ROADRecon web GUI instance.
Run the ROADRecon GUI (default at http://localhost:5000), then start the server with python roadrecon_mcp_server.py (optionally set ROADRECON_URL for a different address). Connect with Claude Desktop via Settings → Servers → Add Server → Add from running server.
Python 3.8+ and a running ROADRecon instance with the web GUI accessible. An MCP-compatible client (e.g., Claude Desktop) is required to use the server.
Set the `ROADRECON_URL` environment variable before starting the server, for example: `ROADRECON_URL=http://localhost:8080 python roadrecon_mcp_server.py`.
It exposes resources such as users, groups, applications, service principals, devices, MFA status, directory roles, role definitions, app roles, OAuth2 permission grants, tenant details, and summary statistics.
Tools include `find_privileged_users()`, `analyze_mfa_status()`, `find_applications_with_secrets()`, `analyze_groups()`, `identify_stale_accounts()`, `analyze_pim_implementation()`, `analyze_service_principal_credentials()`, `analyze_legacy_authentication()`, and `analyze_conditional_access_policies()`.
Prompts cover security posture, privileged access, application risks, identity security, stale accounts, privileged access management, service principal security, legacy authentication risks, conditional access, and a comprehensive security review. Claude can invoke these prompts when connected.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
MCP Toolbox for Databases is an open source MCP server for databases.

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w
Hindsight: Agent Memory That Learns
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
Comments