AI agents call get_distinct_values 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.
This is a read-only query operation that retrieves distinct values from a column for analytical purposes. It does not create, modify, delete, or execute arbitrary code. The blast radius of misuse is minimal—an agent could learn about data cardinality and distribution, but cannot alter or corrupt data. Low severity due to limited potential for harm.
From the tool's definition Tool description states 'Show distinct values and their counts for a column' - retrieves and displays data without modification. No side effects mentioned.
Attacks that exploit this kind of access
Show distinct values and their counts for a column. Useful for understanding enums, statuses, categories, and other low-cardinality columns. 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_distinct_values: 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_distinct_values 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_distinct_values 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_distinct_values. 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_distinct_values 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 →