AI agents call read_table_rows to retrieve information from Mssql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a database table using filters and pagination, which is a classic Read operation. It has no side effects—it does not create, modify, delete, or execute code. The blast radius of misuse is low; an agent could over-query or access sensitive data, but cannot alter the database state.
From the tool's definition Tool name 'read_table_rows' and description 'Reads rows from a table with optional filtering and pagination' explicitly indicate a retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
Reads rows from a table with optional filtering and pagination. It is categorised as a Read tool in the Mssql MCP Server, which means it retrieves data without modifying state.
Register the Mssql MCP server in PolicyLayer and add a rule for read_table_rows: 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 Mssql. Nothing to install.
read_table_rows 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 read_table_rows 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 read_table_rows. 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.
read_table_rows is provided by the Mssql MCP server (terraco89/mcp-server-mssql). 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 →