Read records from a table with optional conditions, limit, and offset
AI agents call read_records to retrieve information from Mcp Sqlite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves data from a SQLite database table with filtering, pagination, and conditional options. It performs only read operations without side effects. While the server as a whole includes destructive tools like 'delete_records', this specific tool is strictly a data retrieval operation, making it the Read category with low severity.
From the tool's definition Tool name is 'read_records' and description states it 'Read records from a table with optional conditions, limit, and offset' — this is a query operation with no modification or deletion capabilities.
Attacks that exploit this kind of access
Read records from a table with optional conditions, limit, and offset. It is categorised as a Read tool in the Mcp Sqlite MCP Server, which means it retrieves data without modifying state.
Register the Mcp Sqlite MCP server in PolicyLayer and add a rule for read_records: 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 Mcp Sqlite. Nothing to install.
read_records 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_records 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_records. 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_records is provided by the Mcp Sqlite MCP server (mcp-sqlite). 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 →