Odile Gate Oversight
MCP serverRead-only MCP view of Odile Gate runs, held actions, audit log and metrics
- 15 tools
- Remote
- Freemium
- Security
Read-only MCP view of Odile Gate runs, held actions, audit log and metrics

Policy check before risky agent actions, with proof recorded afterwards
Runs locallyAllow, deny or step-up checks on AI agent writes, with a tamper-evident log
Runs locallyAsk a human to approve an irreversible agent action and get a signed receipt
Pre-payment checks, spend budgets and human approval for agents paying x402 sellers
Verify who controls a phone, email or domain, and get signed human approvals
Phone-callback confirmation and signed receipts before an AI agent makes a payment
Not checked yet
Action catalog and approval policy that let agents run server tasks without SSH
Not checked yetA policy check your agent calls before paying: allow, ask a human, or veto
Not checked yetReview and block risky AI agent actions, installs and MCP calls on your machine
Runs locallyApache-2.0 SDK for hash-chained agent audit logs, policy checks and human approvals
Runs locallyGive AI agents governed SQL access to production databases with masking and approvals
Not checked yetCheck a crypto address, token or signing request for risk before your agent acts
Runs locallyPer-account allow, ask or block rules for what AI apps may do in your connected services
Not checked yet
Per-app keys, allowed calls, approvals and an audit log in front of your API or model key
Not checked yetLogs AI browser agents into sites, handles 2FA codes and asks you before risky steps
Not checked yetSpending control for AI agents: owner-approved budgets, a decision before each payment
Not checked yet
Hand CAPTCHAs, 2FA codes, approvals and sign-ins from your agent to a human with one tap
Not checked yet
Set up approval pipelines, escalation paths and teams in withHuman through an agent
Not checked yet
Spending controls for agent payments: caps, allowed hosts and human approval for x402 APIs
Runs locallyApproval inbox that lets an AI agent propose actions and wait for a human decision
Not checked yetPermission broker that lets AI assistants use your connected accounts without sharing
Not checked yetApproval and budget checks that pause an AI agent before it spends, deploys or sends
Not checked yetCommit-time policy gate for AI agent writes: ALLOW, DENY or STEP_UP with audit receipts
Runs locally
Governance for company AI agents: pre-action checks, approvals and an audit trail over MCP
Not checked yet