Get sample data from a table.
AI agents call get_sample_data to retrieve information from Mcp Openmetadata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves existing sample data from a table without creating, modifying, deleting, or executing any operations. It is a read-only query operation with minimal blast radius—exposure would only allow viewing of sample data that already exists in OpenMetadata.
From the tool's definition Tool description states "Get sample data from a table" with no modification, deletion, or execution capability. Server description confirms it "retrieves" metadata and data. No side effects or state changes occur.
Attacks that exploit this kind of access
Get sample data from a table. It is categorised as a Read tool in the Mcp Openmetadata MCP Server, which means it retrieves data without modifying state.
Register the Mcp Openmetadata MCP server in PolicyLayer and add a rule for get_sample_data: 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 Mcp Openmetadata. Nothing to install.
get_sample_data 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_sample_data 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_sample_data. 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_sample_data is provided by the Mcp Openmetadata MCP server (pfldy2850/mcp-openmetadata). 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 →