AI agents call get_indexes 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 tool retrieves database metadata about indexes without any side effects. It performs introspection only—listing and displaying existing index information. No data is created, modified, deleted, or executed. It falls squarely into the Read category as a schema/metadata query operation. Severity is low because misuse poses minimal risk; an agent querying index information cannot damage data or systems.
From the tool's definition Tool description states it 'List indexes across the database or for a specific table' with retrieval of metadata (index name, columns, uniqueness, index type, filter expressions).
Attacks that exploit this kind of access
List indexes across the database or for a specific table. Shows index name, columns, uniqueness, index type (btree/hash/gin/etc.), and partial index filter expressions. 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_indexes: 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_indexes 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_indexes 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_indexes. 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_indexes 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 →