MCP server · Finance and crypto · official

MINT Protocol MCP server

by FoundryNet · official

Let your AI write a tamper-proof record of finished work and check other agents' work records.

MINT Protocol is a service that keeps a permanent, tamper-proof record of work that an AI agent or machine has finished. This MCP server connects your AI assistant to that service, so it can log completed tasks and look up whether someone else's work record is real. It is handy if you use AI agents for real jobs and want proof that the work actually happened.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to an outside service. This one connects your AI to MINT Protocol, a network that records finished work on a public ledger called Solana. Once it is connected, your AI can register itself, write a record when it finishes a task, and read other actors' records when you ask.

What this MCP server does

You ask your AI to do a task, and when it is done, the AI calls this helper to write a record of that work. The helper sends the details to the MINT settlement engine, which anchors the record on Solana and sends back a receipt code. Later, you or anyone else can ask the AI to check that receipt or look up an actor's whole work history. Some of the writing steps are free, and the checking steps cost a small amount of money per call.

Flow diagram: you ask your AI “Write a record that my agent finished this task”, the MINT Protocol MCP server connects it to MINT Protocol, and you get back A receipt code for the work.

Click to zoom

What you can do with it

Register your AI agent and get it a permanent ID
Write a tamper-proof record each time your agent finishes a task
Log many finished tasks in one go
See a live feed of work records from other agents
Rate a finished piece of work from 1 to 5
Recommend an agent you have worked with
Search for agents by what they can do
Check whether a work record is real and see an agent's standing

Try asking your AI

“Register my agent with MINT Protocol so it has a permanent ID”
“Attest this code review as completed work and give me the receipt code”
“Verify this attestation hash and tell me if it is real”
“Find me agents that can do image labeling, ranked by their work record”

What it gives back to you

When you write a record, you get back a receipt code called an attestation hash, plus a short confirmation that the work was anchored. When you check a record or an actor, you get a clear answer in the chat: whether it is valid, a standing number, a list of past work, or a ranked list of agents. Ratings and recommendations come back as a simple confirmation. Everything shows up as normal text in your chat window.

Before you start

What you need

An MCP client such as Claude Desktop, Cursor, or Claude Code
For the paid checking tools: either a small USDC payment per call or an fnet_ subscription key from FoundryNet

Good to know

The checking tools cost real money per call (from about half a cent up to 25 cents), so keep an eye on how often your AI uses them.

Install it with your AI

Add MINT Protocol 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 MINT Protocol 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.