AI agents call count_tables to retrieve information from Dm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries database metadata to return a count of tables in a schema. It performs no data modification, deletion, or code execution. It is a pure read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'count_tables' and description '统计指定SCHEMA下的表数量' (count the number of tables in a specified SCHEMA) indicate a query operation that retrieves metadata without modification.
Attacks that exploit this kind of access
统计指定SCHEMA下的表数量，不指定则统计默认SCHEMA. It is categorised as a Read tool in the Dm MCP Server, which means it retrieves data without modifying state.
Register the Dm MCP server in PolicyLayer and add a rule for count_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 Dm. Nothing to install.
count_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 count_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 count_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.
count_tables is provided by the Dm MCP server (tgich/dm_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 →