freee取引一覧を取得
AI agents call list_deals to retrieve information from freee MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a list of deals/transactions from freee accounting software. It performs a data retrieval operation with no side effects, permissions changes, or data modifications. Even though freee is financial software, merely reading transaction data poses minimal risk—the exposure is limited to data disclosure rather than moving money or making commitments.
From the tool's definition Tool name 'list_deals' and description '取引一覧を取得' (get transaction list) indicate retrieval/query operation with no modification. Consistent with sibling read tools like 'get_trial_balance_bs', 'list_accounts', 'list_companies', 'list_invoices'.
Attacks that exploit this kind of access
freee取引一覧を取得. It is categorised as a Read tool in the freee MCP Server MCP Server, which means it retrieves data without modifying state.
Register the freee MCP Server MCP server in PolicyLayer and add a rule for list_deals: 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.
list_deals is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_deals 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 list_deals. 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.
list_deals 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 →