compare_batch_jobs
AI agents call compare_batch_jobs to retrieve information from Dataproc MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to compare attributes or results of batch jobs, which is fundamentally a data retrieval and analysis function with no side effects. Without an explicit description stating otherwise, and given the context of sibling read-only tools (get_batch_job, list_batch_jobs), this is classified as Read.
From the tool's definition Tool name 'compare_batch_jobs' suggests a comparison operation that retrieves or analyzes data from existing batch jobs without modifying them.
Attacks that exploit this kind of access
compare_batch_jobs. It is categorised as a Read tool in the Dataproc MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dataproc MCP Server MCP server in PolicyLayer and add a rule for compare_batch_jobs: 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 Dataproc MCP Server. Nothing to install.
compare_batch_jobs 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 compare_batch_jobs 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 compare_batch_jobs. 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.
compare_batch_jobs is provided by the Dataproc MCP Server MCP server (warrenzhu25/dataproc-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 →