AI agents call check_spec_health to retrieve information from Ilograph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to assess the health/status of a specification, which is a diagnostic read operation. No description is available, reducing confidence slightly, but context from related tools (all read-only documentation and validation operations) and the 'check' naming convention indicate this is a diagnostic query with no side effects. Low severity due to read-only nature and limited blast radius.
From the tool's definition Tool name 'check_spec_health' and empty description; the 'check' verb suggests inspection or verification without modification.
Attacks that exploit this kind of access
check_spec_health. It is categorised as a Read tool in the Ilograph MCP Server, which means it retrieves data without modifying state.
Register the Ilograph MCP server in PolicyLayer and add a rule for check_spec_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 Ilograph. Nothing to install.
check_spec_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_spec_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_spec_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_spec_health is provided by the Ilograph MCP server (quincymillerdev/ilograph-mcp-server). 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 →