AI agents use add_mint to create or update resources in MCP Money — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Money environment.
This tool modifies wallet state by adding a new mint, which is a reversible configuration change. It does not execute arbitrary code, delete data irreversibly, or move money directly. However, adding a mint could enable subsequent financial transactions, so it warrants medium severity as a precursor action in a financial context.
From the tool's definition Tool name is 'add_mint' with description 'Add a mint to the wallet'. The verb 'add' indicates creation or modification of wallet configuration state.
Documented attack patterns abuse exactly the kind of access add_mint gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Money, and nothing reaches the server without passing your rules. This is the rule we recommend for add_mint:
{
"version": "1",
"default": "deny",
"tools": {
"add_mint": {
"limits": [
{
"counter": "add_mint_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_mint stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add a mint to the wallet. It is categorised as a Write tool in the MCP Money MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Money MCP server in PolicyLayer and add a rule for add_mint: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Money. Nothing to install.
add_mint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_mint rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for add_mint. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
add_mint is provided by the MCP Money MCP server (pablof7z/mcp-money). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Money, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 MCP Money tools catalogued and risk-classified — across an index of 43,000+ MCP servers.