Access Pretorin compliance systems, controls, evidence, and narratives from your AI tools.
Beta — Pretorin is currently in closed beta. Framework/control browsing works for everyone. Platform write features (evidence, narratives, monitoring) require a beta code. Sign up for early access.
Pretorin CLI gives developers and AI agents direct access to compliance data, implementation context, and evidence workflows.
mcp-name: io.github.pretorin-ai/pretorin
pretorin agent run and route model calls through Pretorin /v1 endpoints.pretorin mcp-serve and connect the MCP server to your existing AI tool (Claude Code, Codex CLI, Cursor, etc.).uv tool install pretorin
pretorin login
pretorin skill installRun the walkthrough:
bash scripts/demo-walkthrough.shUse this flow when you want pretorin agent run to go through Pretorin-hosted model endpoints.
pretorin loginpretorin config set model_api_base_url https://platform.pretorin.com/v1pretorin agent doctor
pretorin agent installpretorin agent run "Assess AC-2 implementation gaps for my system"Key behavior:
pretorin login with no shell-level OPENAI_API_KEY override.OPENAI_API_KEY -> config.api_key -> config.openai_api_key.OPENAI_API_KEY is set in your shell, it overrides stored login credentials.Use this flow when you already have an AI agent/tool and want Pretorin as an MCP capability provider.
<img src="assets/Rome-bot_Basic-1.png" alt="Rome-bot" width="120" align="right">The Pretorin skill teaches your AI agent how to use MCP tools effectively for compliance workflows. Install it for Claude Code and/or Codex CLI:
pretorin skill install # both agents
pretorin skill install --agent claude # claude only
pretorin skill install --agent codex # codex only
pretorin skill status # check what's installedclaude mcp add --transport stdio pretorin -- pretorin mcp-serveTeam setup via .mcp.json:
{
"mcpServers": {
"pretorin": {
"type": "stdio",
"command": "pretorin",
"args": ["mcp-serve"]
}
}
}Add to ~/.codex/config.toml:
[mcp_servers.pretorin]
command = "pretorin"
args = ["mcp-serve"]If you installed Pretorin with uv tool install or pipx, prefer pinning the absolute path from command -v pretorin to avoid PATH drift between shells and GUI apps.
For Claude Desktop, Cursor, and Windsurf setup, see docs/MCP.md.
Platform-backed review and update workflows are single-scope: set one active system + framework first with pretorin context set, then run evidence, note, monitoring, narrative, or MCP-assisted compliance commands inside that scope. Multi-framework work must be split into separate runs. Evidence, narratives, and notes all support a local-first workflow: create locally, list, then push to the platform.
| Command | Purpose |
|---|---|
pretorin frameworks list | List available frameworks |
pretorin frameworks control <framework> <control> | Get control details and guidance |
pretorin context set | Set active system/framework context |
pretorin context show | Inspect and validate the active context |
pretorin context clear | Clear the active context |
pretorin evidence create | Create local evidence file |
pretorin evidence list | List local evidence files |
pretorin evidence push | Push local evidence to Pretorin |
pretorin evidence search | Search platform evidence |
pretorin evidence upsert <ctrl> <fw> | Find-or-create evidence and link it |
pretorin narrative create | Create local narrative file |
pretorin narrative list | List local narrative files |
pretorin narrative push | Push local narratives to Pretorin |
pretorin narrative get <ctrl> <fw> | Get current control narrative |
pretorin narrative push-file <ctrl> <fw> <sys> <file> | Push a single narrative file |
pretorin notes create | Create local note file |
pretorin notes list --local | List local note files |
pretorin notes push | Push local notes to Pretorin |
pretorin notes list <ctrl> <fw> | List platform control notes |
pretorin notes add <ctrl> <fw> --content ... | Add control note directly |
pretorin monitoring push | Push a monitoring event |
pretorin agent run "<task>" | Run Codex-powered compliance task |
pretorin review run --control-id <id> --path <dir> | Review local code for control coverage |
pretorin skill install | Install Pretorin skill for AI agents |
pretorin skill status | Check skill install status per agent |
pretorin mcp-serve | Start MCP server |
Quick context checks:
pretorin context show --quiet
pretorin context show --quiet --checkpretorin login clears the stored active context when you switch API keys or platform endpoints, which helps prevent old localhost or deleted-system scope from leaking into a new environment.
Credentials are stored at ~/.pretorin/config.json.
| Variable | Description |
|---|---|
PRETORIN_API_KEY | API key for platform access (overrides stored config) |
PRETORIN_PLATFORM_API_BASE_URL | Platform REST API base URL (/api/v1/public) |
PRETORIN_API_BASE_URL | Backward-compatible alias for PRETORIN_PLATFORM_API_BASE_URL |
PRETORIN_MODEL_API_BASE_URL | Model API base URL used by agent/harness flows (default: https://platform.pretorin.com/v1) |
OPENAI_API_KEY | Optional model key override for agent runtime |
Full documentation is built with mdbook. To view it locally:
# Install mdbook (if you don't have it)
cargo install mdbook
# Serve the docs and open in your browser
cd docs && mdbook serve --openThis starts a local server at http://localhost:3000 with live-reload.
To build static HTML without serving:
cd docs && mdbook build
# Output is in docs/book/git clone https://github.com/pretorin-ai/pretorin-cli.git
cd pretorin-cli
uv pip install -e ".[dev]"
pytest
ruff check src/pretorin
ruff format --check src/pretorinMIT License. See LICENSE.