AI agents call get_sample to retrieve information from Omnibase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_sample retrieves data without side effects. It supports filtering and sorting but only for data retrieval purposes. The emphasis on table name validation and the explicit 'preview' nature indicate this is a safe read operation. No data is created, modified, deleted, or executed—only queried.
From the tool's definition Tool description states 'Preview rows from a table' with 'optional WHERE filtering and ORDER BY sorting'. This is clearly a query operation with no modification capability. Table name validation prevents injection attacks.
Attacks that exploit this kind of access
Preview rows from a table. Table name is validated against schema to prevent injection. Supports optional WHERE filtering and ORDER BY sorting. It is categorised as a Read tool in the Omnibase MCP Server, which means it retrieves data without modifying state.
Register the Omnibase MCP server in PolicyLayer and add a rule for get_sample: 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 Omnibase. Nothing to install.
get_sample 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 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. 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 is provided by the Omnibase MCP server (omnibase-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 →