AI agents call get_sql_file_allowed_dirs to retrieve information from Dm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns metadata about file system permissions/configuration. It does not create, modify, delete, or execute anything—it simply retrieves informational data. The return value is a list of allowed directory paths, which is a read-only operation. The low severity reflects minimal blast radius: misuse would only expose directory path information, not cause data loss or unauthorized modifications.
From the tool's definition Tool name and description indicate it retrieves a list of allowed directories for SQL file execution. The description '获取 execute_sql_file 允许读取的 SQL 文件目录' translates to 'Get the SQL file directories allowed to be read by execute_sql_file', which is a query…
Attacks that exploit this kind of access
获取 execute_sql_file 允许读取的 SQL 文件目录。. It is categorised as a Read tool in the Dm MCP Server, which means it retrieves data without modifying state.
Register the Dm MCP server in PolicyLayer and add a rule for get_sql_file_allowed_dirs: 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 Dm. Nothing to install.
get_sql_file_allowed_dirs 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 get_sql_file_allowed_dirs 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 get_sql_file_allowed_dirs. 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.
get_sql_file_allowed_dirs is provided by the Dm MCP server (tgich/dm_mcp_server). 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 →