fw is the command-line tool for migrations, tenant setup, policy bundles, tool
registries, MCP servers, sessions, approvals, exports, audit verification and replay. Commands
that change a tenant write an audit record before they run, so the operator action itself is part
of the chain.
cargo build --release -p fw-cli # Run migrations as the database owner. target/release/fw --database-url "$OWNER_URL" migrate # Seed a demo tenant, provider and gateway API key. target/release/fw --database-url "$OWNER_URL" seed \ --tenant demo \ --upstream http://127.0.0.1:9000 # Create the audit checkpoint signing seed and print its public key. target/release/fw --database-url "$OWNER_URL" audit keygen # Verify a tenant's audit chain against the pinned public key. target/release/fw --database-url "$OWNER_URL" audit verify \ --tenant demo \ --public-key <pinned-public-key>
| Group | What it does |
|---|---|
| Database | Apply migrations, undo a migration, create the restricted application role, check partition ranges. |
| Tenant setup | Create tenants, principals, API keys, provider routes, model catalog entries, budgets, session limits and link allow-lists. |
| Policy | Initialize, validate, diff, build and activate Cedar bundles. Activating a bundle is denied on an unaccepted loosening. |
| Tools | Import or sync the tool registry, list tools, approve a tool pin, and inspect whether a tool description has changed. |
| MCP servers | Add servers, set credentials from stdin or an env var, sync tool lists, remove servers, generate master keys. |
| Sessions | Show session state, declassify taint for a named human, set budgets, session limits, approval TTL and link allow-lists. |
| Approvals and notifiers | List, show, approve, deny or expire approvals. Add, list, enable, disable and test webhook, Slack or email notifiers. |
| Audit | Generate signing keys, verify hash chains and checkpoints, replay recorded decisions, and compare what a candidate bundle would have decided. |
| Exports | Add export sinks, filters, cursors, and tenant-level destinations for SIEM, warehouse, Kafka, S3, OTLP, webhook, syslog or files. |
| Detection | Manage pattern rules, score inputs, benchmark classifier backends, and run calibration with a recorded report hash. |
# Policy bundles fw bundle init --team staff --out grants.cedar fw bundle build --tenant demo --policies grants.cedar fw bundle activate --tenant demo --bundle <hash> # Tool registry fw tools import --tenant demo --yaml tools.yaml fw tools list --tenant demo fw tools status --tenant demo --tool files/read_file --status approved # MCP servers fw mcp add --tenant demo --name ws --url https://mcp.example.test fw mcp set-credential --tenant demo --name ws fw mcp sync --tenant demo --name ws # Sessions, budgets and declassification fw session show --tenant demo --session <session-id> fw session limits-set --tenant demo --session-calls 200 --session-spend 50 fw session declassify --tenant demo --session <session-id> --by operator --reason "reviewed page" # Replay and what-if fw replay --tenant demo --from 2026-11-01 --to 2026-11-13 --limit 1000 fw replay --tenant demo --bundle <candidate-bundle-hash>
The exact flags depend on the build, but this is the shape the CLI uses for routine operator work: tenant-scoped commands, explicit bundle hashes, audit-first writes, and no secrets in command lines.
Commands that mutate a tenant — keys, tools, bundles, MCP servers, sessions, notifiers, export sinks — write an admin_action record before the change is applied.
Provider credentials and MCP credentials come from stdin or a named environment variable. The audit trail records the command shape without secret flags.
fw audit verify exits 1 when it sees edited records, gaps, forged records, bad signatures, wrong checkpoints, or a tail that disagrees with the chain head.
Replay compares stored Cedar inputs with the recorded verdict. Records that lack replay data, bundles, or policy-decided evidence are counted separately rather than reported as reproductions.