List all departments flattened across offices
AI agents call list_departments to retrieve information from Mcp Cvpartner 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 department information without creating, modifying, deleting, or executing any actions. It is a pure data retrieval operation consistent with the Read category. The low severity reflects minimal blast radius if misused by an AI agent—returning department lists poses no risk of data destruction, financial impact, or unintended execution.
From the tool's definition Tool name 'list_departments' and description 'List all departments flattened across offices' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all departments flattened across offices. It is categorised as a Read tool in the Mcp Cvpartner MCP Server, which means it retrieves data without modifying state.
Register the Mcp Cvpartner MCP server in PolicyLayer and add a rule for list_departments: 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 Mcp Cvpartner. Nothing to install.
list_departments 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_departments 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_departments. 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_departments is provided by the Mcp Cvpartner MCP server (@snokam/mcp-cvpartner). 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 →