get_dataset_queries
AI agents call get_dataset_queries to retrieve information from DataHub 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 suggests fetching or listing queries attached to a dataset, which is a read operation with no mutation or side effects. The empty description reduces confidence slightly, but the naming convention and server context (exploration and understanding, not modification) strongly indicate this retrieves existing metadata rather than executing or modifying queries.
From the tool's definition Tool name 'get_dataset_queries' indicates retrieval of existing queries associated with a dataset. Server description emphasizes 'search, explore data lineage' and 'understand business context' as read operations.
Attacks that exploit this kind of access
get_dataset_queries. It is categorised as a Read tool in the DataHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DataHub MCP Server MCP server in PolicyLayer and add a rule for get_dataset_queries: 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 DataHub MCP Server. Nothing to install.
get_dataset_queries 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_dataset_queries 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_dataset_queries. 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_dataset_queries is provided by the DataHub MCP Server MCP server (shemreader/mcp-server-datahub). 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 →