Retrieves a list of all departments in the organization.
AI agents call get_department_list to retrieve information from DingDing MCP 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 organizational structure data without creating, modifying, deleting, or executing any operations. It is a straightforward data retrieval function typical of Read category tools. Severity is low because exposure of department lists presents minimal risk—this is organizational metadata that is typically not sensitive or actionable without additional context.
From the tool's definition Tool name 'get_department_list' and description 'Retrieves a list of all departments' indicate a read-only query operation with no side effects.
Attacks that exploit this kind of access
Retrieves a list of all departments in the organization. It is categorised as a Read tool in the DingDing MCP MCP Server, which means it retrieves data without modifying state.
Register the DingDing MCP server in PolicyLayer and add a rule for get_department_list: 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 DingDing MCP. Nothing to install.
get_department_list 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_department_list 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_department_list. 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_department_list is provided by the DingDing MCP server (wllcnm/dingding-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 →