glue_table
AI agents call glue_table to retrieve information from Duckdb Iceberg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The server is explicitly designed for querying and reading data from Iceberg tables. The sibling tools are all Read operations (describe_table inspects schema, list_tables enumerates tables, query_lakehouse runs read queries). The 'glue_table' tool almost certainly retrieves or describes a table from Glue without modifying it.
From the tool's definition Tool name 'glue_table' with no description provided. Based on sibling tools (describe_table, list_tables, query_lakehouse) and server purpose of querying Iceberg tables, this likely retrieves table metadata or returns table information from AWS Glue Data…
Attacks that exploit this kind of access
glue_table. It is categorised as a Read tool in the Duckdb Iceberg MCP Server, which means it retrieves data without modifying state.
Register the Duckdb Iceberg MCP server in PolicyLayer and add a rule for glue_table: 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 Duckdb Iceberg. Nothing to install.
glue_table 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 glue_table 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 glue_table. 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.
glue_table is provided by the Duckdb Iceberg MCP server (ys1173/duckdb-iceberg-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 →