Get permissions for a Databricks object with parameters: object_type (required, e.g.,
AI agents call get_permissions to retrieve information from Databricks Permissions MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries existing permission configurations. However, severity is elevated to medium because permission data is sensitive—it reveals access control information that could enable privilege escalation or targeted attacks if exposed to a compromised agent. The tool itself is not dangerous, but the data it exposes is valuable to an attacker.
From the tool's definition Tool is named 'get_permissions' and performs a retrieval operation ('Get permissions'). The description indicates it retrieves permission data for Databricks objects without modifying state.
Attacks that exploit this kind of access
Get permissions for a Databricks object with parameters: object_type (required, e.g.,. It is categorised as a Read tool in the Databricks Permissions MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Databricks Permissions MCP Server MCP server in PolicyLayer and add a rule for get_permissions: 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 Databricks Permissions MCP Server. Nothing to install.
get_permissions 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_permissions 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_permissions. 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_permissions is provided by the Databricks Permissions MCP Server MCP server (justtryai/databricks-permissions-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 →