Your AI assistant.
Your compliance data.
ConfigCobra ships a native MCP server. Connect it to Claude, ChatGPT, Cursor, or any MCP-compatible AI — then ask anything about your Microsoft 365 security posture in plain language. No dashboard. No exports. No waiting.
The answer is in your compliance data. Getting to it takes too long.
Your ConfigCobra assessment holds every finding, every per-user detail, every remediation step — but accessing it means logging in, navigating, filtering, and exporting. The MCP server eliminates that. Your AI reads the data directly and answers in plain English, the moment you ask.
One integration. Different questions for every role.
Find exactly who's blocking your compliance score — in one question.
Plain-language executive briefings. No dashboard, no exports.
Query every client tenant from a single AI conversation.
Pull all the evidence you need. Ask for it in plain English.
Three things. One connection.
The MCP server sits between your AI assistant and your ConfigCobra assessment data. It exposes your live compliance results — findings, evidence, posture score, per-user details — as a set of tools your AI can call in real time.
- Connect once with Microsoft OAuth — your credentials never leave Microsoft
- Your AI queries your most recent assessment data in real time
- Read-only — your AI can answer questions but cannot change anything
- Works with Claude, ChatGPT, Cursor, and any MCP-compatible client
- No extra agents, no scripts, no data exports
Works with the AI you already use.
Any tool that supports MCP over HTTP/SSE can connect. View the full setup guide →
Common questions
This is just the start. Sentra goes further.
Today your AI assistant can query your existing CIS compliance data via MCP. With Sentra, the AI becomes the auditor — evaluating your tenant against CIS, NIS2, ISO 27001, SOC 2, and DORA, in plain language, on demand. Same Microsoft connector. Purpose-trained model.