証憑(レシート・請求書)をfreeeにアップロード
AI agents use upload_receipt to create or update resources in freee MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your freee MCP Server environment.
Uploading receipts modifies the accounting system state by adding new document records, making this a Write operation rather than Read. While it creates financial documentation, it does not directly move money or create financial obligations (Financial category), nor does it execute arbitrary code (Execute).
From the tool's definition Tool name 'upload_receipt' and description indicating uploading receipts/invoices (証憑 = voucher/receipt, アップロード = upload) to freee accounting system. This is a file/document upload operation that creates records.
Attacks that exploit this kind of access
証憑(レシート・請求書)をfreeeにアップロード. It is categorised as a Write tool in the freee MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the freee MCP Server MCP server in PolicyLayer and add a rule for upload_receipt: 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 freee MCP Server. Nothing to install.
upload_receipt 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 upload_receipt 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 upload_receipt. 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.
upload_receipt is provided by the freee MCP Server MCP server (unson-llc/freee-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 →