Crea un borrador de gasto y devuelve preguntas faltantes para poder confirmarlo.
AI agents use expense.capture to create or update resources in Mcp Finance — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Finance environment.
The tool creates a draft expense record (write operation), which is reversible since it is only a draft pending confirmation. It does not move money or commit financial obligations directly — it captures data for later confirmation. Severity is medium because it writes financial data to the system, but it cannot finalize transactions on its own.
From the tool's definition Crea un borrador de gasto
Attacks that exploit this kind of access
Crea un borrador de gasto y devuelve preguntas faltantes para poder confirmarlo. It is categorised as a Write tool in the Mcp Finance MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Finance MCP server in PolicyLayer and add a rule for expense.capture: 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 Mcp Finance. Nothing to install.
expense.capture 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 expense.capture 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 expense.capture. 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.
expense.capture is provided by the Mcp Finance MCP server (toothlesstarantula/mcp-finance). 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 →