AI agents call check_local_integrity to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes database integrity metadata without creating, modifying, or deleting any data. It is a diagnostic/inspection operation that queries the state of a local SQLite database. No side effects occur beyond reporting the results of validation checks. This clearly falls into the Read category as it retrieves information for analysis purposes only.
From the tool's definition The tool "check_local_integrity" performs validation checks on local SQLite database state including quick_check, foreign keys, bridge validation, backup counts, and orphan rows.
Attacks that exploit this kind of access
Check local SQLite quick_check, foreign keys, bridge validation, backup-relevant counts, and orphan rows. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for check_local_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_local_integrity 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 check_local_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_local_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_local_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 →