AI agents use create_table_from_s3 to create or update resources in Duckdb — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Duckdb environment.
This tool creates (writes) a new table in the database, which is a reversible modification. It does not execute arbitrary code, delete data, move money, or perform financial operations. The severity is medium because unauthorized table creation could consume resources, overwrite existing schemas, or expose S3 data unnecessarily, but the effect is reversible via table deletion.
From the tool's definition Tool name 'create_table_from_s3' and description 'Create a table from an S3 path' indicate it creates a new table in the DuckDB database by loading data from S3. This is a write operation that modifies the database state reversibly.
Attacks that exploit this kind of access
Create a table from an S3 path. It is categorised as a Write tool in the Duckdb MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Duckdb MCP server in PolicyLayer and add a rule for create_table_from_s3: 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. Nothing to install.
create_table_from_s3 is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_table_from_s3 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 create_table_from_s3. 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.
create_table_from_s3 is provided by the Duckdb MCP server (synehq/mcp-server-duckdb). 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 →