AI agents use budget_set to create or update resources in AgentOS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AgentOS environment.
This tool creates or modifies budget limit settings, which is a reversible write operation. While it affects resource constraints, it does not directly execute code, delete data irreversibly, or move money. The severity is medium because misconfiguration could cause legitimate tasks to be terminated or blocked, impacting agent operations, but the effects are reversible by updating the budget again.
From the tool's definition Tool name 'budget_set' and description 'Set a budget limit for a session or task to track resource usage' indicates creating or modifying budget configuration data.
Attacks that exploit this kind of access
Set a budget limit for a session or task to track resource usage. It is categorised as a Write tool in the AgentOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AgentOS MCP server in PolicyLayer and add a rule for budget_set: 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 AgentOS. Nothing to install.
budget_set 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 budget_set 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 budget_set. 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.
budget_set is provided by the AgentOS MCP server (netflypsb/agentos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →