mcp_get_job_error
AI agents call mcp_get_job_error to retrieve information from Databricks MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly suggests it retrieves error details from a Databricks job without modifying state. No evidence of destructive, financial, or side-effect-triggering behavior. This is a read-only diagnostic operation with minimal blast radius if misused by an agent, as it only exposes error logs or status information already generated by prior operations.
From the tool's definition Tool name 'mcp_get_job_error' indicates retrieval of error information; 'get' prefix and 'error' suffix are consistent with data retrieval operations. Description is empty, limiting direct confirmation.
Attacks that exploit this kind of access
mcp_get_job_error. It is categorised as a Read tool in the Databricks MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for mcp_get_job_error: 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. Nothing to install.
mcp_get_job_error 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 mcp_get_job_error 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 mcp_get_job_error. 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.
mcp_get_job_error is provided by the Databricks MCP Server MCP server (stephenjhsu/databricks-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 →