AI agents call check_ai_health to retrieve information from Devon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries status information about DEVONthink's AI health. Health checks are non-destructive read operations that only inspect system state and return status information. There is no side effect, data modification, code execution, or financial impact. This is a straightforward monitoring/diagnostic operation.
From the tool's definition Tool name 'check_ai_health' and description indicate a health check operation that queries the state of DEVONthink's AI system without modifying or executing operations on data.
Attacks that exploit this kind of access
Check if DEVONthink. It is categorised as a Read tool in the Devon MCP Server, which means it retrieves data without modifying state.
Register the Devon MCP server in PolicyLayer and add a rule for check_ai_health: 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 Devon. Nothing to install.
check_ai_health 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_ai_health 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_ai_health. 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_ai_health is provided by the Devon MCP server (mnott/devon). 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 →