Provides a list of iceberg tables from the Iceberg catalog for a given namespace
AI agents call get_iceberg_tables to retrieve information from IcebergMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available tables in an Iceberg data lakehouse. It has no side effects, does not execute queries against data, and does not modify or delete any state. The blast radius of misuse is minimal—an agent could enumerate tables to understand data structure, but cannot access, modify, or harm actual data through this tool alone.
From the tool's definition Tool description states it 'Provides a list of iceberg tables from the Iceberg catalog' — a retrieval operation with no modification or destructive capability.
Documented attack patterns abuse exactly the kind of access get_iceberg_tables gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and IcebergMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_iceberg_tables:
{
"version": "1",
"default": "deny",
"tools": {
"get_iceberg_tables": {}
}
}get_iceberg_tables is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Provides a list of iceberg tables from the Iceberg catalog for a given namespace. It is categorised as a Read tool in the IcebergMCP MCP Server, which means it retrieves data without modifying state.
Register the Iceberg MCP server in PolicyLayer and add a rule for get_iceberg_tables: 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 IcebergMCP. Nothing to install.
get_iceberg_tables 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_iceberg_tables 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_iceberg_tables. 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_iceberg_tables is provided by the Iceberg MCP server (ryft-io/iceberg-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 IcebergMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 IcebergMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.