MCP server · Security
Trust Ledger OS MCP server
by Cubiczan
Lets your AI record, review, and look up trust decisions for risky changes before they go live.
Trust Ledger OS is a helper for teams that use AI agents and want a paper trail. It watches over big changes, like code going out or money being spent, and keeps a record of who approved what. It is handy if you work with AI agents and need to show that someone checked things before they happened.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another tool. This one connects your AI to Trust Ledger OS, so it can send a change in for review, get a decision back, and look up past decisions. You just ask in plain words, and the helper does the running around.
What this MCP server does
You tell your AI about a change, a spend request, or an action an agent wants to take. The AI passes that to this helper, which checks it against your team's trust rules and product policy. It attaches a trace of the runtime decision, then gives back an approve, deny, or counter answer. The decision gets stored in a ledger so future runs can look it up. When you ask later, the AI can read that ledger and tell you what was decided and why.
Click to zoomWhat you can do with it
- Submit a code change, spend request, or agent action for review
- Get an approve, deny, or counter decision back
- Look up past decisions in the ledger
- Check a decision against your domain's trust floor
- See the trace attached to a runtime decision
- Confirm whether a human lock was required
Try asking your AI
- “Review this change against our trust rules and tell me if it can go out”
- “Look up the last decision we made about the payment service”
- “Was a human approval needed for this agent action”
- “Show me the ledger entries from this week”
What it gives back to you
You get back a decision: approve, deny, or counter, along with the reason and the trace that was attached. If you ask for ledger entries, you get a list of past decisions with their details. Everything shows up as normal text in your chat, so you can read it and copy it into a ticket or a message.
Before you start
What you need
- Node.js installed on your computer
- The Trust Ledger OS package, which you install with a command
- A folder where the ledger file can be written
Good to know
This helper can record decisions and enforce human locks, so if it is set up wrong it could block changes that should go through or let ones through that should not.
Install it with your AI
Add Trust Ledger OS MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Trust Ledger OS MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Teams using AI agents who need a clear record of who approved risky changes, like platform engineers, AI ops folks, and anyone doing release or spend reviews.
