Set or clear the auto-forward recipient for rewards. When a recipient is set,
AI agents use set_reward_recipient 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 creates or modifies a reward recipient configuration, which is a Write operation (reversible state change). However, severity is high rather than medium because: (1) it operates within a financial system (Tempo blockchain stablecoin payments), (2) misconfiguration could redirect rewards to unintended addresses, and (3) it affects autonomous payment flows where an AI agent error could cause financial losses.
From the tool's definition "Set or clear the auto-forward recipient for rewards" - modifies reward distribution configuration by setting or clearing a recipient address, which is a reversible change to payment routing logic.
Documented attack patterns abuse exactly the kind of access set_reward_recipient 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 set_reward_recipient:
{
"version": "1",
"default": "deny",
"tools": {
"set_reward_recipient": {
"limits": [
{
"counter": "set_reward_recipient_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_reward_recipient 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.
Set or clear the auto-forward recipient for rewards. When a recipient is set,. 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 set_reward_recipient: 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.
set_reward_recipient 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 set_reward_recipient 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 set_reward_recipient. 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.
set_reward_recipient 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.