获取数据库中的所有表。
AI agents call get_tables to retrieve information from CockroachDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a retrieval operation to list database tables, which is a standard metadata query with no side effects. It does not modify data, execute arbitrary code, delete resources, or involve financial operations. The blast radius of misuse is minimal—an attacker gains only visibility into table structure, not data access or the ability to modify the database.
From the tool's definition Tool name is 'get_tables' and description states it retrieves ('获取') all tables from the database. This is a read-only operation that queries metadata without modifying, deleting, or executing code.
Attacks that exploit this kind of access
获取数据库中的所有表。. It is categorised as a Read tool in the CockroachDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CockroachDB MCP Server MCP server in PolicyLayer and add a rule for get_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 CockroachDB MCP Server. Nothing to install.
get_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_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_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_tables is provided by the CockroachDB MCP Server MCP server (swayingleaves/cockroachdb-mcp-server). 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 →