Grant a TIP-20 role to an address. Requires DEFAULT_ADMIN_ROLE on the token.
AI agents use grant_role to create or update resources in Tempo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tempo environment.
This tool grants privileged roles on a financial/stablecoin smart contract. While technically a 'write' operation (modifying access control state), the blast radius is critical: granting roles could allow an attacker to mint tokens, bypass compliance checks, blacklist/whitelist addresses, or perform other high-impact operations on the Tempo stablecoin system.
From the tool's definition Grant a TIP-20 role to an address. Requires DEFAULT_ADMIN_ROLE on the token.
Documented attack patterns abuse exactly the kind of access grant_role gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tempo, and nothing reaches the server without passing your rules. This is the rule we recommend for grant_role:
{
"version": "1",
"default": "deny",
"tools": {
"grant_role": {
"limits": [
{
"counter": "grant_role_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}grant_role 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.
Grant a TIP-20 role to an address. Requires DEFAULT_ADMIN_ROLE on the token. It is categorised as a Write tool in the Tempo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tempo MCP server in PolicyLayer and add a rule for grant_role: 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 Tempo. Nothing to install.
grant_role 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 grant_role 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 grant_role. 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.
grant_role is provided by the Tempo MCP server (arome3/tempo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tempo, 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.
61 Tempo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.