AI agents call show_profile_health to retrieve information from Ogham without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and displays diagnostic information about a profile's state (memory count, graph visualization). It has no side effects, makes no modifications to data, and poses minimal risk if misused by an AI agent—at worst, an agent would retrieve information it should not see. It is clearly a Read operation that retrieves or displays data without reversible or irreversible changes.
From the tool's definition Tool name 'show_profile_health' and description 'Visual dashboard showing profile health: memory count, graph' indicate this retrieves and displays metrics/statistics. No modification, deletion, or execution of arbitrary code occurs.
Attacks that exploit this kind of access
Visual dashboard showing profile health: memory count, graph. It is categorised as a Read tool in the Ogham MCP Server, which means it retrieves data without modifying state.
Register the Ogham MCP server in PolicyLayer and add a rule for show_profile_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 Ogham. Nothing to install.
show_profile_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 show_profile_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 show_profile_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.
show_profile_health is provided by the Ogham MCP server (ogham-mcp/ogham-mcp). 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 →