Check the health of the MCP server and Databricks connection.
AI agents call health to retrieve information from Databricks MCP Server Template 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 diagnostic tool that queries the status of system components. It has no side effects, does not execute code or SQL, does not modify data, and does not perform financial operations. The blast radius of misuse is minimal — an AI agent cannot cause harm by repeatedly calling a health check endpoint.
From the tool's definition Tool is named 'health' and described as checking 'the health of the MCP server and Databricks connection' — a diagnostic operation that retrieves status information without modifying any data or executing operations.
Attacks that exploit this kind of access
Check the health of the MCP server and Databricks connection. It is categorised as a Read tool in the Databricks MCP Server Template MCP Server, which means it retrieves data without modifying state.
Register the Databricks MCP Server Template MCP server in PolicyLayer and add a rule for health: 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 MCP Server Template. Nothing to install.
health 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 health 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 health. 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.
health is provided by the Databricks MCP Server Template MCP server (max-nienu/mnienu-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 →