List all tables in the database
AI agents call list-tables to retrieve information from ODBC MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves database schema metadata (table names) with no side effects, creation, modification, deletion, or code execution. It is a benign informational query consistent with the server's read-only design. Severity is low because exposing table names poses minimal risk; the actual data access requires separate execute-query calls with additional permissions.
From the tool's definition Tool name 'list-tables' and description 'List all tables in the database' indicate retrieval of metadata without modification. Server description emphasizes 'read-only safeguards' and the tool is a sibling to other introspection/query operations.
Attacks that exploit this kind of access
List all tables in the database. It is categorised as a Read tool in the ODBC MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ODBC MCP Server MCP server in PolicyLayer and add a rule for list-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 ODBC MCP Server. Nothing to install.
list-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 list-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 list-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.
list-tables is provided by the ODBC MCP Server MCP server (tylerstoltz/mcp-odbc). 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 →