# AGISafe (agisafe.ai)

> Pre-deployment safety cases for frontier AI.

Structured, procurement-ready safety cases for frontier and AGI-class systems — from self-assessment to independent evidence the regulator and your board will accept.

## What this is
AGISafe is a vertical in the CSOAI Hive — EU AI Act / NIS2 / DORA compliant tooling exposed as Model Context Protocol (MCP) servers callable by any AI agent.

## MCP tools
- eu-ai-act-compliance-mcp.assess: Run a structured EU AI Act risk assessment from any agent or workflow.
- agisafe-mcp.build_safety_case: Generate a pre-deployment safety case for a frontier model programmatically.

## Discovery
- Agent card: https://agisafe.ai/agent.json
- MCP catalog: https://agisafe.ai/.well-known/mcp.json
- Sitemap: https://agisafe.ai/sitemap.xml
- Hive registry: https://csoai.org (271 published MCP servers)

## Pricing
See https://agisafe.ai/pricing/