Quickstart

Governance in minutes

Install the plugin (mandatory enforcement) and add the MCP server (agent-facing tools). Both auto-provision a free account on first run — no signup required.

Already have an API key?

Drop it into VAIBOT_API_KEY or ~/.vaibot/credentials.json and the install will use it instead of bootstrapping a new account.

Prefer to start in the dashboard?

Sign up with email, then grab a key from Settings → API.

1

Install for your agent

Pick your stack. Each path auto-provisions a free account (1,000 governed decisions/month, no credit card) on first run.

The happy path uses both surfaces. The plugin enforces governance before every tool call (mandatory). The MCP server lets your agent call 15 governance tools directly — query pending approvals, view receipts, approve in-session.

1. Install the plugin (mandatory enforcement)
shell
# Auto-bootstraps a free account on first tool call.
npm install -g @vaibot/claudecode-circuitbreaker-plugin
claude --plugin-dir $(npm root -g)/@vaibot/claudecode-circuitbreaker-plugin
2. Add the MCP server (agent-facing governance tools)
shell
# OAuth flow auto-provisions an account if you don't already have one,
# or links to the account the plugin just bootstrapped.
claude mcp add --transport http vaibot https://api.vaibot.io/v2/mcp

# Then in Claude Code:  /mcp  → click vaibot → complete OAuth.

Both surfaces work standalone, but installed together you get mandatory enforcement plus self-service tools the agent can call mid-task.

2

Run any tool call

The plugin or MCP OAuth flow auto-provisions a free account on first use. Plugin users find their API key at ~/.vaibot/credentials.json — MCP-OAuth users have it stored by their agent. Confirm the account is alive:
shell
# Returns ok:true plus your account ID, wallet, claimed status, and quota.
curl -H "authorization: Bearer $VAIBOT_API_KEY" \
  https://api.vaibot.io/v2/accounts/me

# {
#   "ok": true,
#   "account_id": "0x...",
#   "wallet_address": "0x...",
#   "claimed": false,
#   "quota": { "used": 0, "limit": 1000, "remaining": 1000, "month": "2026-05" }
# }
3

Claim your account (optional)

Bootstrap accounts get a synthetic email by default. Connect a real email so you can sign into the dashboard and approve pending actions from there. Skip if you only need enforcement.
4

Switch from observe to enforce when ready

The plugin defaults to observe — it logs governance verdicts but lets every tool through. Flip to enforcewhen you're comfortable with what it would have blocked.
shell
export VAIBOT_MODE=enforce

# Enforce blocks denied tools and pauses on approval_required decisions.
# Observe still logs everything, just doesn't intercept.

Verify it's working

After a few tool calls, this should show your decision count incrementing.

shell
curl -H "authorization: Bearer $VAIBOT_API_KEY" \
  https://api.vaibot.io/v2/observability/chain-completeness

# {
#   "ok": true,
#   "window": "1h",
#   "decides_total": 3,
#   "decides_completed": 3,
#   "completion_rate_percent": 100,
# }
Open the dashboard

Plugin vs. MCP server

Two complementary surfaces. Most deployments use both — the plugin enforces, the MCP server gives the agent in-session governance tools.

Plugin (enforcement)
  • ✓ Mandatory pre-execution check
  • ✓ Tamper-evident audit trail
  • ✓ Local circuit breaker fallback
  • ✗ Agent cannot query governance state
MCP server (agent tools)
  • ✓ Agent calls vaibot_status, vaibot_pending, etc.
  • ✓ In-session approve / deny
  • ✗ Optional, not enforcing
  • ✗ Agent could choose to skip it

Available MCP tools

Once the MCP server is configured, the agent can call these tools directly.

vaibot_decide
Evaluate a proposed agent action against your policy
vaibot_finalize
Record the final outcome after an allowed action executes
vaibot_approve
Approve a pending high-risk action
vaibot_deny
Deny a pending high-risk action
vaibot_receipts
List recent governance receipts for your project
vaibot_receipt_get
Fetch a specific governance receipt by ID
vaibot_verify
Verify a provenance proof for a governance receipt
vaibot_status
Get your account status, quota, and plan info
vaibot_recent
Get recent decisions for quick review
vaibot_pending
List all actions awaiting human approval
vaibot_summary
Get a governance summary for a run or time window
vaibot_preview
Preview how a policy would classify an action
vaibot_policy
View or update your project policy configuration
vaibot_link
Generate a shareable receipt verification link
vaibot_set_account_email
Set or claim the email for your account

Currently showing instructions for Claude Code.