AI agents invoke check_database_integrity to trigger actions in Todos. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes SQLite PRAGMA statements against a local database. While these are read-like diagnostic operations, they actively run commands against the database engine rather than simply querying data passively. PRAGMA quick_check and foreign key validation are database engine operations (Execute category).
From the tool's definition Run PRAGMA quick_check and foreign key validation on local SQLite DB
Attacks that exploit this kind of access
Run PRAGMA quick_check and foreign key validation on local SQLite DB. It is categorised as a Execute tool in the Todos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Todos MCP server in PolicyLayer and add a rule for check_database_integrity: 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 Todos. Nothing to install.
check_database_integrity is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the check_database_integrity 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 check_database_integrity. 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.
check_database_integrity is provided by the Todos MCP server (@hasna/todos). 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 →