Create or update budget data
AI agents use upsert_budget to create or update resources in Lunch Money MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lunch Money MCP Server environment.
Upserting budget data creates or modifies budget entries in a financial management app. This is a Write operation (reversible create/update), but carries high severity because incorrect budget data could mislead financial planning and AI-driven financial decisions. It does not directly move money, so Financial is not applicable, but the financial context elevates the risk.
From the tool's definition 'Create or update budget data' — upsert operation modifies financial planning data reversibly
Attacks that exploit this kind of access
Create or update budget data. It is categorised as a Write tool in the Lunch Money MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lunch Money MCP Server MCP server in PolicyLayer and add a rule for upsert_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 Lunch Money MCP Server. Nothing to install.
upsert_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 upsert_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 upsert_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.
upsert_budget is provided by the Lunch Money MCP Server MCP server (matiasl13/lunchmoney-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 →