Describe a table (blocked if outside endpoint scope).
AI agents call get_table_schema to retrieve information from Database MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries database schema metadata without side effects. It retrieves table structure information (columns, types, constraints, etc.) for inspection purposes. The scope blocking mechanism is a security control rather than a capability indicator. Paired with sibling tools like get_all_schemas and get_tables, this is clearly part of a read-only introspection API.
From the tool's definition Tool name 'get_table_schema' and description 'Describe a table' indicate schema inspection/retrieval with no modification. Verb 'Describe' and 'get' prefix are characteristic of read operations.
Attacks that exploit this kind of access
Describe a table (blocked if outside endpoint scope). It is categorised as a Read tool in the Database MCP MCP Server, which means it retrieves data without modifying state.
Register the Database MCP server in PolicyLayer and add a rule for get_table_schema: 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 Database MCP. Nothing to install.
get_table_schema 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_table_schema 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_table_schema. 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_table_schema is provided by the Database MCP server (swoiow/database_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 →