KopplaSAFE
A Model-Context-Protocol (MCP) Server for Active Directory
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Koppla is a model-context-protocol server for Active Directory that enables you to manage users, groups, and computer objects using natural language.
For more information, visit https://lazyadmin.nl/koppla
With Koppla, you can seamlessly query and manage your Active Directory environment using Claude Desktop or other MCP capable AI agents. ---
🔹 What Can Koppla Do?
Koppla allows you to execute complex Active Directory queries and updates effortlessly. Examples:
- "Find all inactive users who haven't logged in for 90 days."
- "Add John Doe to the 'IT Admins' security group."
- "List all locked-out user accounts."
- "Find all users in the Sales department."
- "Which groups does Jane Smith belong to?"
- "Show me empty groups."
- "Find users in group A but not in group B."
🚀 Getting Started
1️⃣ Prerequisites
- Python 3.7 or higher
- Active Directory environment
- Claude Desktop application (for integration with Claude)
2️⃣ Installation
Koppla requires Python and can be installed using:
pip install koppla
3️⃣ Configuration
Using the Configuration Manager (Recommended)
Koppla includes a secure configuration manager that handles encryption of sensitive credentials:
koppla-config configure
This interactive tool will:
- Prompt for your Active Directory connection details
- Securely encrypt your password using Fernet symmetric encryption
- Create or update the Claude Desktop configuration file with Koppla server settings
- Automatically create a backup of your existing Claude Desktop configuration
- Test the connection to verify your credentials
You can also:
- Display current configuration:
koppla-config show - Test your AD connection:
koppla-config test
Manual Configuration
Koppla us
6990c6cb4c79OBSERVED · 2026-10-08Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
query_ad | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
ldap3, mcp, python-dotenv, cryptography
assets/Koppla-demo.gif
Gates applied: no_behavioural_pass.
6990c6cb4c79full audit observations/trust-audit/mcp-server/ruudmens__koppla.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 6990c6cb4c79 | SAFE | B | 89 | first audit |
Questions
What is the Koppla MCP server?
A Model-Context-Protocol (MCP) Server for Active Directory
What tools does Koppla expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Koppla safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Koppla need?
It reads AD_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (6990c6cb4c79), read on 2026-10-08. The repository is watched and re-audited when it changes.