Set daily and/or monthly budget limits.
AI agents use set_budget to create or update resources in Agent Cost — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Cost environment.
This tool modifies budget configuration settings, which is a reversible write operation. While budget limits relate to financial oversight, the tool itself does not move money, authorize transactions, or commit financial obligations — it only configures thresholds for cost tracking and alerts.
From the tool's definition Tool named 'set_budget' with description 'Set daily and/or monthly budget limits' — creates or modifies configuration data (budget thresholds) that affects financial tracking and spending controls.
Attacks that exploit this kind of access
Set daily and/or monthly budget limits. It is categorised as a Write tool in the Agent Cost MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Cost MCP server in PolicyLayer and add a rule for set_budget: 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 Agent Cost. Nothing to install.
set_budget 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_budget 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_budget. 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_budget is provided by the Agent Cost MCP server (vanthienha199/agent-cost-mcp). 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 →