Comprehensive system scan across all dimensions: Execution, Revenue, Burnout, and Distribution. Produces an Overall Health Score (1-100) with failure scenario predictions. Use this when the user provides complete startup telemetry covering multiple areas, or when they want a holistic view.
AI agents call generate_full_diagnosis to retrieve information from openGlad without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes startup telemetry data across multiple dimensions to generate a diagnostic report and health score. It retrieves and synthesizes data but does not modify, delete, execute code, or involve financial transactions. Severity is medium because it aggregates sensitive startup metrics and produces failure predictions that could influence high-stakes decisions if misused or misinterpreted.
From the tool's definition Comprehensive system scan across all dimensions... Produces an Overall Health Score (1-100) with failure scenario predictions
Documented attack patterns abuse exactly the kind of access generate_full_diagnosis gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and openGlad, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_full_diagnosis:
{
"version": "1",
"default": "deny",
"tools": {
"generate_full_diagnosis": {}
}
}generate_full_diagnosis is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Comprehensive system scan across all dimensions: Execution, Revenue, Burnout, and Distribution. Produces an Overall Health Score (1-100) with failure scenario predictions. Use this when the user provides complete startup telemetry covering multiple areas, or when they want a holistic view. It is categorised as a Read tool in the openGlad MCP Server, which means it retrieves data without modifying state.
Register the openGlad MCP server in PolicyLayer and add a rule for generate_full_diagnosis: 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 openGlad. Nothing to install.
generate_full_diagnosis 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 generate_full_diagnosis 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 generate_full_diagnosis. 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.
generate_full_diagnosis is provided by the openGlad MCP server (tuguberk/openglad). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from openGlad, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 openGlad tools catalogued and risk-classified — across an index of 43,000+ MCP servers.