统计表中的记录总数
AI agents call get_table_count to retrieve information from PySqlitMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a simple aggregation query to retrieve record counts from a table. This is a passive data retrieval operation with no side effects, no data modification, and no irreversible actions. It falls squarely into the Read category, appropriate for low severity due to minimal blast radius if misused by an agent.
From the tool's definition Tool name is 'get_table_count' and description indicates it 'counts total records in a table' (统计表中的记录总数). This is a read-only query operation that retrieves aggregate count information without modifying any data.
Attacks that exploit this kind of access
统计表中的记录总数. It is categorised as a Read tool in the PySqlitMCP MCP Server, which means it retrieves data without modifying state.
Register the PySqlit MCP server in PolicyLayer and add a rule for get_table_count: 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 PySqlitMCP. Nothing to install.
get_table_count 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_count 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_count. 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_count is provided by the PySqlit MCP server (python51888/pysqlitmcp). 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 →