検索条件に一致するレコードを検索します。
AI agents call fm_find_records to retrieve information from FileMaker 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 data based on search criteria without modifying, deleting, or executing arbitrary operations. It is a read-only database query operation consistent with the FileMaker MCP Server's stated read-only access model. The blast radius of misuse is minimal—an AI agent could retrieve sensitive data but cannot alter or destroy it.
From the tool's definition Tool name 'fm_find_records' and server description stating 'read-only access to FileMaker databases' and 'retrieve records'.
Attacks that exploit this kind of access
検索条件に一致するレコードを検索します。. It is categorised as a Read tool in the FileMaker MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FileMaker MCP Server MCP server in PolicyLayer and add a rule for fm_find_records: 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 FileMaker MCP Server. Nothing to install.
fm_find_records 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 fm_find_records 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 fm_find_records. 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.
fm_find_records is provided by the FileMaker MCP Server MCP server (ta-toshio/filemaker-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 →