Troxy Dashboard

Decisions

0

across all checkpoints

Pending approval

0

needs your action

Blocked

0

-

Escalated

0

user-approved actions

Recent activity

Agent	Target	Value	Decision	Time

Control coverage

What your agents ran past Troxy in this period, across every checkpoint.

All decisions

All types

All agents

Total events

-

Blocked

-

Escalated

-

Block rate

-

Agent	Type	Target	Value	Decision	Policy	Time

Applies to everyone in the workspace, in every space.

For agents on a machine you can open a terminal on: your laptop, a server, a VM. Claude Code, Cursor, GitHub Copilot, Windsurf, Continue, Aider, Codex CLI, or any other MCP-compatible agent. You run one command there and the agent's tools appear in its tool list.

Name	Key	Last used	Expires	Status

Loading…

Token Optimization

How much your AI agents cost to run, and how to spend less

All agents

Last 30 days

Loading…

Conversation

Your rules

Account

Email address

Loading...

Profile

Used to fill in your name and phone automatically during an agent-driven purchase, and to skip asking questions it already knows the answer to.

Full name

Phone

AI Policy Builder model

Always Claude Haiku, the fastest and cheapest tier. Policy conditions don't need a bigger model.

Powered by Claude

Claude Haiku 4.5

Current session

-

Product tour

Replay the 60-second intro that explains what Troxy does.

Plan

Free beta, no limits during beta period. More plans coming after beta.

Beta

My AI tools

The AI coding tools Troxy found on your machine. Run troxy tools to re-scan after installing something new.

Loading…

Notifications

Choose which event outcomes trigger an email.

Notification email

Leave blank to use your account email

Email on block

Event blocked by a policy rule

Email on escalation

Event held for your approval

Email on notify

Event matched a Notify rule

Email on allow

Event approved, high volume, off by default

Escalation

Approval window

How long an escalated event waits before it auto-declines for safety

1 hour

Danger zone

Clear all data

Deletes all events, reports, and policies. Your account and API keys stay active.

Delete account

Permanently deletes all policies, API keys, and activity, agents stop immediately

Delete workspace

Permanently deletes your workspace, its policies, and its AI provider key. Only allowed once every other member has been removed - you can't take anyone else's access with it.

Your workspace

Loading...

Join code

Share this with people you want to add. Regenerating invalidates the old code immediately.

Loading...

Domain restriction

Only allow people with emails from specific domains to join. One domain per line (e.g., @company.com).

Require manual approval for new joiners

Live Model Router

Enable Live Model Router

Automatically swaps simple messages to a cheaper model in real time. Turning this off stops the per-message check entirely, not just the swaps - useful if you'd rather not spend anything on it.

Content Trimming

Enable content trimming

Compresses large, repetitive tool output (test/build logs) before it reaches the model - keeps the start and end, marks what was cut. Off by default while this is new; turn on to try it for real.

Pending approvals

People who requested to join and are waiting for admin approval.

Invite by email

One email per line. Everyone on this list joins with the role picked below.

Workspace Admin

Members

MCP Connectors

Push Troxy's MCP config to every agent in your org — zero install for users. Connectors use each platform's admin API to register Troxy as an MCP server and assign it to all org members instantly.

MCP Connectors

Push Troxy's MCP config to every agent in your org — zero install for users. Connectors use each platform's admin API to register Troxy as an MCP server and assign it to all org members instantly.

AI provider

Optional — nothing else in Troxy needs this. Connecting one unlocks two extras for every member of this org: typing a policy in plain English instead of building it field by field, and one extra recommendation that catches a turn that used an expensive model for a simple task. Set once here instead of every member pasting their own key. Only admins can view or change this.

Billing keys

Optional. Without this, your spend numbers already work — they're calculated from real token counts (token-math), just not pulled from your actual invoice. Connecting a billing key here replaces those estimates with your real bill, org-wide. This only ever applies to org totals and per-model breakdowns — it never attributes to a specific agent. Only admins can view or change these.

This needs an admin-level API key from the provider's own console, not a regular one - and not every account tier offers one. Anthropic's Admin API, for example, is unavailable on an Individual account; it requires a Team or Business organization there. If a sync fails with "invalid or revoked" but you're confident the key is correct, check your provider account's plan tier before assuming the key itself is wrong.